Coding & Dev Tools AI Tools

Hermes Agent

Nous Research's open-weight agentic model for tool-use tasks

Hermes Agent is an agentic AI system by Nous Research built on their Hermes series of open-weight models, optimized for function calling, tool use, and structured outputs. It is designed to handle complex multi-step tasks with reliable JSON output and API interaction. Suited for researchers and developers who want a capable, open-weight model for agentic pipelines.

Openwork

AI agent for automating knowledge work tasks across your tools

Openwork is an AI agent platform that automates repetitive knowledge work by connecting to workplace tools like email, calendars, and documents to complete tasks on behalf of users. It uses agentic reasoning to handle multi-step workflows end-to-end. Targeted at professionals and teams looking to delegate routine digital work to an AI assistant.

OpenCode

Terminal-based AI coding agent powered by any LLM provider

OpenCode is an open-source terminal AI coding assistant that supports multiple LLM backends including OpenAI, Anthropic, and local models. It provides an interactive TUI interface for chatting about code, running edits, and executing terminal commands within a project context. Suited for developers who want a lightweight, provider-agnostic agentic coding CLI.

Claude Code

Anthropic's agentic AI coding tool that lives in your terminal

Claude Code is an official agentic CLI tool by Anthropic that brings Claude directly into the developer's terminal and editor. It can read, write, and refactor files across a codebase, run shell commands, and execute multi-step coding tasks autonomously. Built for developers who want a powerful, safe AI coding agent without leaving their existing workflow.

LM Studio

Discover, download, and run local LLMs with a friendly GUI

LM Studio is a desktop application for discovering, downloading, and running open-source LLMs on Mac, Windows, and Linux using local CPU and GPU resources. It includes a ChatGPT-style chat UI, model library browser, and a local OpenAI-compatible server. Popular with developers and enthusiasts who want effortless local model experimentation.

Msty

Beautiful offline-first desktop app for running local AI models

Msty is a polished desktop AI chat application that runs local models via Ollama and also connects to cloud providers like OpenAI and Anthropic from one interface. It offers conversation branching, model comparison, and document chat. Suited for power users who want a premium UI for both local and cloud LLM interactions.

Jan

Run open-source LLMs fully offline on your own computer

Jan is an open-source desktop application that runs large language models entirely locally on Mac, Windows, and Linux without any cloud dependency. It features a ChatGPT-like interface, an in-app model hub, and OpenAI-compatible API server mode. Perfect for privacy-conscious users and developers who want offline AI without sending data to the cloud.

Google AI Studio

Prototype and test Gemini models with a free browser interface

Google AI Studio is a free, browser-based developer environment for testing and building with the Gemini family of models, including Gemini 1.5 Pro's million-token context. It supports multimodal inputs—text, images, audio, video—and generates API keys and code snippets for fast integration. Ideal for developers exploring Gemini's capabilities before building full applications.

MLflow

Open-source platform to manage the full ML lifecycle end-to-end

MLflow is an open-source platform by Databricks for tracking experiments, packaging models, and managing deployments across the ML lifecycle. It supports any ML library through a simple Python API and stores parameters, metrics, and artifacts automatically. Widely used by data scientists and ML engineers in both research and production environments.

Wren AI

Open-source AI data analyst that speaks SQL to your warehouse

Wren AI is an open-source AI Business Intelligence platform that connects to data warehouses and lets teams query data through natural language. It generates SQL, renders charts, and understands business context via a semantic layer. Designed for data teams and analysts who want self-service analytics without writing SQL.

Helicone AI

Open-source LLM observability: log, monitor, and optimize AI calls

Helicone is an open-source observability platform that proxies LLM API calls to provide logging, cost tracking, latency metrics, prompt versioning, and caching. It integrates with a one-line code change and supports OpenAI, Anthropic, and Azure. Built for AI teams who need production-grade monitoring without heavy infrastructure.

OpenRouter

One API to route requests across 200+ AI models and providers

OpenRouter provides a unified REST API that lets developers access models from OpenAI, Anthropic, Google, Meta, Mistral, and dozens more through a single endpoint. It handles provider fallback, cost comparison, and rate-limit routing automatically. Ideal for developers and startups building model-agnostic AI applications.

Repomix

Pack your entire repo into one AI-friendly file instantly

Repomix is an open-source CLI tool that bundles an entire codebase into a single, well-formatted text file suited for LLM ingestion. It supports XML, Markdown, and plain text output, respects .gitignore, and offers token count estimates. Great for developers who need to feed large codebases to AI models efficiently.

Together AI

Run and fine-tune leading open-source LLMs at cloud scale

Together AI is a cloud platform for deploying, fine-tuning, and serving open-source foundation models such as Llama, Mistral, and FLUX at high throughput. It offers a unified API compatible with OpenAI's interface and dedicated GPU instances. Ideal for AI teams building production applications who need cost-efficient, scalable inference.

Vanna.ai

Train an AI model on your schema and query data in plain English

Vanna.ai is an open-source Python framework that lets you fine-tune a retrieval-augmented LLM on your own database schema and query history. It translates natural language questions into accurate SQL and can run in a notebook or Slack bot. Designed for data teams who need a customizable, private text-to-SQL solution.

aider

AI pair programmer that edits your codebase from the terminal

aider is an open-source command-line tool that lets developers pair-program with GPT-4, Claude, and other LLMs directly in their terminal. It reads repo context, applies multi-file edits, and commits changes with meaningful messages automatically. Best suited for developers who prefer a CLI-first, git-integrated AI coding workflow.

Lovable

Build full-stack web apps from a prompt with no code

Lovable is an AI full-stack app builder that generates React frontends backed by Supabase databases from plain-English descriptions. Users can iterate on features through conversational prompts, deploy instantly, and connect custom domains. Targeted at founders, product managers, and developers who want to ship apps without boilerplate.

AI For Developers

Curated AI tools and resources built for developers

AI For Developers is a curated directory of AI tools, APIs, and resources tailored specifically for software engineers and developers. It surfaces practical AI integrations, libraries, and services to help developers build smarter applications faster. The platform focuses on actionable, developer-centric AI resources rather than general consumer tools.

Windsurf

Agentic AI IDE that codes alongside you in real time

Windsurf (by Codeium) is an AI-native IDE built around an agentic assistant called Cascade that can plan, write, and execute multi-step coding tasks. It features deep codebase awareness, in-editor chat, and autonomous file editing. Designed for professional developers who want an AI partner that acts, not just suggests.

Continue

Open-source AI code assistant that plugs into your IDE

Continue is an open-source AI coding assistant that integrates directly into VS Code and JetBrains IDEs. It supports any LLM provider—OpenAI, Anthropic, local models—for inline completions, chat, and refactoring. Developers get full control over model choice and context, making it ideal for teams wanting flexible, self-hostable AI coding workflows.

Amazon Q

AWS's AI assistant for business built for cloud and code

Amazon Q is AWS's generative AI-powered assistant tailored for business and software development use cases. It helps developers write, debug, and explain code within IDEs, and assists enterprise users with querying internal data, generating reports, and automating workflows using AWS services. Deeply integrated with the AWS ecosystem for cloud-native teams.

SEAL LLM Leaderboard

Scale AI's expert-evaluated leaderboard for LLM capabilities

The SEAL (Scale Evaluation and Assessment of Language Models) Leaderboard by Scale AI provides rigorous, expert-human-evaluated rankings of LLMs across domains like coding, instruction following, math, and reasoning. Unlike automated benchmarks, SEAL uses human raters to assess model quality. It is a trusted reference for enterprises and AI researchers selecting models for demanding applications.

Read AI

AI meeting assistant that summarizes, transcribes, and scores meetings

Read AI is an AI-powered meeting assistant that automatically joins video calls on Zoom, Google Meet, and Teams to transcribe, summarize, and extract action items. It also provides engagement scores and speaker analytics to improve meeting effectiveness. Widely used by teams seeking to reduce manual note-taking and capture insights from every meeting.

DeepSeek

China's frontier open-source LLM rivaling the world's best

DeepSeek is a Chinese AI lab offering a series of highly capable open-source large language models, including DeepSeek-V2 and DeepSeek-R1, which rival proprietary models on reasoning and coding benchmarks. The models are available via API and for self-hosting. DeepSeek attracted global attention for delivering frontier performance at low cost.

Qwen

Alibaba's powerful open-source LLM family for diverse tasks

Qwen is Alibaba Cloud's series of large language models available in multiple sizes, excelling at multilingual tasks, coding, math, and reasoning. Many Qwen models are released open-source, making them accessible for research and commercial deployment. The family includes specialized variants for vision, audio, and long-context understanding.

Shotstack Workflows

Automate video production pipelines with a no-code AI workflow builder

Shotstack Workflows is a visual automation platform that lets developers and businesses chain together video editing, rendering, and AI media tasks without writing complex code. It integrates with APIs, media libraries, and AI services to produce personalized video content at scale.

Myriad

Generate diverse AI content prompts to spark creative ideas fast

Myriad is a free AI content prompt tool by NamePepper that helps writers, marketers, and creators generate varied prompt ideas for blog posts, social content, and campaigns. It quickly surfaces angles and hooks so teams can beat creative blocks and produce content more efficiently.

AI-Flow

Build and connect AI model pipelines visually with no code

AI-Flow is an open-source visual tool for connecting multiple AI models and APIs into automated pipelines using a node-based interface. Developers and researchers can chain GPT, Stable Diffusion, and other services together to build complex AI workflows without writing glue code.

Interview Solver

Solve coding interview problems in real time with AI assistance

Interview Solver provides real-time AI guidance during technical coding interviews, helping candidates work through data structures, algorithms, and system design questions. It acts as a discreet co-pilot for developers preparing for or sitting FAANG-style interviews.

Promptly

Build and share AI-powered apps without writing code

Promptly is a no-code platform for building, deploying, and sharing AI-powered applications and chatbots. Users can chain prompts, connect data sources, and embed assistants into their workflows or products. It's designed for teams and individuals who want to harness LLMs without engineering overhead.

ChatGPT prompt engineering for developers

DeepLearning.AI short course on prompt engineering with GPT

A free short course by DeepLearning.AI and OpenAI, taught by Isa Fulford and Andrew Ng, covering best practices for prompting ChatGPT in application development. Topics include iterative prompt refinement, summarization, inference, transformation, and building chatbots. Ideal for developers integrating LLMs into software products.

GitHub Copilot

AI pair programmer that writes code alongside you in real time

GitHub Copilot is an AI-powered coding assistant developed by GitHub and OpenAI, integrated directly into editors like VS Code, JetBrains, and Neovim. It suggests code completions, generates entire functions, writes tests, and explains code based on context. Widely used by developers to accelerate software development and reduce boilerplate.

Mutiny

Personalize your website for every visitor without writing code

Mutiny is a no-code AI personalization platform that helps B2B companies tailor website content, messaging, and CTAs to different audience segments based on firmographic and behavioral data. It integrates with CRMs like Salesforce and HubSpot to drive pipeline and conversion. Trusted by revenue and growth teams at enterprise SaaS companies.

Civitai

Discover and share Stable Diffusion models, LoRAs, and more

Civitai is the leading open community hub for sharing, downloading, and rating Stable Diffusion models, LoRAs, embeddings, and VAEs. It hosts tens of thousands of user-contributed models spanning every style and subject, with detailed previews and prompt examples. It's an essential resource for AI artists and researchers who want to extend their image generation capabilities with community-made fine-tunes.

SalesAgent Chat

AI sales agent that converts website visitors into qualified leads

SalesAgent Chat is an AI-powered chatbot platform that engages website visitors with personalized sales conversations, qualifies leads, and books meetings automatically. It is built for B2B sales teams who want to increase pipeline without scaling their SDR headcount.

Ollama

Run large language models locally on your own machine

Ollama is an open-source tool that makes it easy to download and run state-of-the-art large language models like Llama, Mistral, and Gemma locally on macOS, Linux, and Windows. It provides a simple CLI and API, giving developers and privacy-conscious users full control over their AI without sending data to the cloud.

co:here

Enterprise NLP platform for building production-grade AI apps

Cohere provides enterprise-focused large language model APIs for text generation, embedding, classification, and semantic search. Its platform is optimized for business use cases and offers deployment flexibility including on-premises and private cloud options, targeting developers and enterprises building reliable, scalable NLP applications.

Keploy

Auto-generate API tests and mocks from real traffic recordings

Keploy is an open-source testing platform that automatically generates unit tests, integration tests, and data mocks by recording live API traffic from an application. It dramatically reduces the manual effort needed to write and maintain tests, helping backend engineering teams improve code coverage and catch regressions faster.

LangChain

The leading framework for building LLM-powered applications

LangChain is an open-source Python and JavaScript framework that provides the core abstractions and integrations for building applications powered by large language models, including agents, RAG pipelines, and tool-using systems. It is the most widely adopted LLM application framework, used by developers ranging from hobbyists to Fortune 500 engineering teams.

Portia AI

Agentic AI platform that plans and executes complex tasks reliably

Portia AI is an agentic workflow platform that helps developers build reliable AI agents capable of multi-step task planning and execution. It provides tools for agent memory, tool use, and clarification handling so agents can complete complex real-world tasks autonomously. Designed for teams building production-grade AI pipelines.

LMQL

A programming language for constrained and efficient LLM interaction

LMQL (Language Model Query Language) is an open-source programming language designed for interacting with large language models. It lets developers write queries that constrain LLM outputs using control flow, types, and scripting logic, enabling structured generation and reduced token waste. Ideal for developers who need deterministic, structured responses from LLMs.

Langfuse

Open-source LLM observability and prompt management platform

Langfuse is an open-source platform for tracing, monitoring, and debugging LLM applications. It captures traces of prompts, completions, and tool calls to help teams detect issues, measure costs, and improve quality. It also offers prompt versioning and A/B testing, making it a comprehensive LLMOps tool for engineering teams.

Phoenix

Open-source AI observability platform for evaluating LLM apps

Phoenix by Arize is an open-source observability and evaluation tool for AI and LLM applications. It provides tracing, dataset management, and built-in evaluators to measure hallucination, relevance, and toxicity. Designed for ML engineers and data scientists who need deep insight into model and agent behavior during development and production.

Prediction Guard

Secure, compliant API gateway for enterprise LLM deployments

Prediction Guard provides a secure API layer for accessing and deploying LLMs with built-in safety, compliance, and data privacy controls. It screens inputs and outputs for PII, toxicity, and factual consistency, making it suitable for regulated industries. Teams use it to integrate AI safely without exposing sensitive data to third-party models.

ChatWithCloud

AI-powered assistant for querying and managing cloud infrastructure

ChatWithCloud is a natural language interface that lets users interact with their cloud infrastructure through conversational AI. It enables querying AWS, GCP, or Azure resources, diagnosing issues, and getting cost insights without writing CLI commands. Designed for DevOps engineers and cloud architects who want faster access to infrastructure insights.

SinglebaseCloud

Backend-as-a-service platform built for AI-native applications

SinglebaseCloud is a backend-as-a-service platform that provides a database, authentication, file storage, and vector search in a single unified API. It is optimized for AI applications that need fast vector similarity search alongside traditional data storage. Aimed at developers building AI-powered apps who want to avoid managing separate backend services.

Maxim AI

LLM evaluation and testing platform for production AI quality

Maxim AI is an evaluation and testing platform that helps teams measure and improve the quality of LLM-powered applications. It supports prompt testing, regression tracking, and custom evaluators to catch regressions before deployment. Designed for AI engineers and product teams who need systematic quality assurance for generative AI features.

Wordware

No-code AI application builder using natural language prompts

Wordware is a no-code platform that lets teams build AI-powered workflows and applications using natural language as the primary interface. Users can compose multi-step AI pipelines, connect external tools, and deploy apps without writing code. Ideal for non-technical teams and founders who want to ship AI products quickly.

Pagerly

AI-powered on-call and incident management inside Slack

Pagerly is an on-call and incident management platform that integrates directly into Slack, enabling teams to handle alerts, rotations, and escalations without leaving their chat tool. It uses AI to summarize incidents, suggest responders, and automate runbook actions. Built for DevOps and SRE teams who manage on-call workflows at scale.

Hexabot

Open-source chatbot builder for multi-channel AI conversations

Hexabot is an open-source chatbot building platform that enables teams to create and deploy AI-powered conversational bots across multiple channels including web, WhatsApp, and Messenger. It provides a visual flow editor, NLP integration, and plugin support for customization. Aimed at developers and businesses who want full control over their chatbot stack.

AI/ML API

Unified API marketplace for 200+ AI and machine learning models

AI/ML API is a single API platform that aggregates access to over 200 AI models including LLMs, image generators, speech, and embeddings from providers like OpenAI, Anthropic, and Stability AI. It offers competitive pricing, pay-per-use billing, and OpenAI-compatible endpoints. Ideal for developers who want one integration point for multiple AI capabilities.

Opik

Open-source LLM evaluation and tracing platform by Comet

Opik is an open-source LLM evaluation and observability tool from Comet that helps teams trace, evaluate, and debug AI applications. It provides tracing of LLM calls, dataset management, and built-in and custom evaluators for measuring output quality. Designed for ML engineers who need a production-ready evaluation pipeline integrated with their experiment tracking.

Kiln

AI fine-tuning and dataset curation platform for custom models

Kiln is a platform for fine-tuning large language models and managing training datasets with a collaborative, visual interface. Teams can curate examples, run fine-tuning jobs, and compare model versions to improve task-specific performance. Built for ML teams and product engineers who want to customize models without deep infrastructure expertise.

Cleanlab

Find and fix label errors in datasets using AI-powered data curation

Cleanlab's Trustworthy Language Model (TLM) is an AI service that detects unreliable or hallucinated outputs from LLMs by assigning confidence scores to generated answers. It helps teams identify when model responses are likely wrong before they reach end users. Essential for enterprises deploying LLMs in high-stakes domains where factual accuracy is critical.

TensorZero

LLM gateway for production optimization, routing, and fine-tuning

TensorZero is an open-source LLM gateway that collects production inference data and uses it to continuously optimize prompts, route to better models, and generate fine-tuning datasets. It wraps existing LLM APIs and learns from real user feedback and outcomes to improve quality over time. Built for ML teams who want to systematically improve production AI systems.

StarOps

AI-powered DevOps automation platform for cloud operations

StarOps by Ingenimax is an AI DevOps automation platform that helps teams manage cloud infrastructure, deployments, and incident response using intelligent automation. It offers natural language interfaces for infrastructure operations and integrates with existing DevOps toolchains. Targeted at engineering and platform teams looking to reduce manual operational overhead.

AgentDock

Open platform for building and deploying customizable AI agents

AgentDock is an open-source framework for building, configuring, and deploying AI agents with modular tool integrations. It supports connecting agents to APIs, databases, and custom logic nodes through a visual and code-first interface. Designed for developers who want full control over agent architecture and tool orchestration.

Codeflash

AI tool that automatically optimizes Python code for performance

Codeflash is an AI-powered Python performance optimization tool that automatically finds and rewrites slow code to make it faster. It generates optimized versions of functions, validates correctness with tests, and benchmarks improvements before suggesting changes. Built for Python developers and data engineers who want measurable performance gains without manual profiling.

Rysa AI

AI-powered real estate research and property intelligence platform

Rysa AI is an AI platform for real estate professionals that provides property research, market analysis, and investment insights through conversational AI. Users can query property data, comparable sales, and neighborhood trends using natural language. Designed for agents, investors, and analysts who want to speed up real estate due diligence.

OpenAI Codex

OpenAI's code-specialized AI model powering developer tools

OpenAI Codex is an AI model trained on billions of lines of code that translates natural language into functional code across dozens of programming languages. It powers GitHub Copilot and is available via API for building custom coding assistants and developer tools. Best suited for developers building code generation, completion, and explanation features into their products.

Ghostwriter

Replit's AI coding assistant for in-browser development and debugging

Ghostwriter is Replit's built-in AI coding assistant that provides code completion, explanation, debugging, and generation directly inside the Replit IDE. It understands the full project context and can refactor code or answer questions about the codebase in real time. Ideal for students, hobbyists, and developers building and learning directly in Replit's cloud environment.

GoCodeo

AI-powered full-stack app builder for rapid web development

GoCodeo is an AI coding assistant and app builder that helps developers scaffold, generate, and iterate on full-stack web applications using natural language prompts. It supports popular frameworks and integrates with existing codebases to accelerate feature development. Targeted at developers and startups who want to ship web apps faster with AI assistance.

Stenography

Automatically generates documentation for any codebase using AI

Stenography is an AI tool that reads source code and automatically generates plain-English documentation, docstrings, and inline comments. It integrates with VS Code and GitHub to document codebases continuously as code changes. Built for developers and teams who want to maintain up-to-date documentation without writing it manually.

Mintlify

Beautiful AI-powered documentation platform for developer products

Mintlify is a documentation platform that enables teams to create, host, and maintain beautiful developer documentation with built-in AI features like a chatbot trained on your docs. It supports MDX, OpenAPI spec imports, and component-rich pages with minimal configuration. Designed for developer-facing products that need professional documentation with a great user experience.

AI2sql

Generate accurate SQL queries from natural language in seconds

AI2sql is an AI tool that converts plain English questions into accurate SQL queries for popular databases including MySQL, PostgreSQL, MSSQL, and BigQuery. Users input their schema and a natural language question and receive a ready-to-run query. Designed for business analysts, data teams, and non-technical users who need to query databases without knowing SQL.

CodiumAI

AI tool that generates meaningful tests for your code automatically

CodiumAI (now Qodo) is an AI-powered testing tool that analyzes your code and automatically generates comprehensive unit tests, edge cases, and integration tests. It integrates with VS Code and JetBrains and explains its test suggestions to help developers understand coverage gaps. Aimed at software engineers who want to improve test quality and coverage without writing boilerplate tests.

MutableAI

AI software engineer that refactors and evolves your codebase

MutableAI is an AI coding platform that reads your repository and performs intelligent refactoring, documentation, and code generation at a project-wide level. It goes beyond single-file suggestions to understand cross-file context and make consistent changes across a codebase. Built for engineering teams who want an AI collaborator capable of handling larger-scale code transformations.

FlexApp

Build internal tools and apps with AI, no coding required

FlexApp is an AI-powered no-code platform for building internal business applications, dashboards, and CRUD tools by describing requirements in natural language. It connects to databases and APIs and auto-generates forms, tables, and workflows. Designed for operations teams and non-technical business users who need custom internal tools without engineering resources.

Capacity

AI-powered support automation platform for enterprise help desks

Capacity is an AI-driven support automation platform that connects to your knowledge base, ticketing system, and internal tools to automatically answer employee and customer questions. It features a conversational AI layer on top of tools like Salesforce, Zendesk, and SharePoint to deflect repetitive tickets. Built for enterprise support and IT teams looking to reduce ticket volume and improve self-service.

Runcell

AI-powered Jupyter notebook assistant for data science workflows

Runcell is an AI assistant for Jupyter notebooks that helps data scientists generate, explain, debug, and optimize code cells using natural language. It understands notebook context including previous cells and outputs to provide accurate, relevant suggestions. Designed for data scientists and analysts who want AI assistance tightly integrated into their notebook workflow.

Gopher

DeepMind's 280B parameter language model for research

Gopher is a 280-billion parameter large language model developed by DeepMind, designed to advance understanding of language model capabilities and limitations at scale. It was evaluated across 152 diverse tasks and demonstrated strong performance in reading comprehension, fact-checking, and knowledge-intensive domains. Released as a research model, it also included a companion paper on ethical considerations and societal impact.

OPT

Meta's open pretrained transformer language models for researchers

OPT (Open Pretrained Transformers) is a suite of open-source large language models from Meta AI, ranging from 125M to 175B parameters, designed as a reproducible and accessible alternative to GPT-3. The models are available on Hugging Face for research purposes and are trained on publicly available datasets. OPT aims to enable the broader research community to study large language model behavior and limitations.

Bloom

Open multilingual LLM trained by 1,000+ researchers worldwide

BLOOM is a 176-billion parameter open-access multilingual language model developed collaboratively by over 1,000 AI researchers through the BigScience project. It supports 46 natural languages and 13 programming languages, making it one of the most linguistically diverse LLMs available. BLOOM is freely available on Hugging Face and is designed for researchers and developers needing a transparent, open-source alternative to proprietary models.

Stable Beluga

Stability AI's instruction-tuned 65B LLM built on LLaMA

Stable Beluga is a 65-billion parameter language model from Stability AI, fine-tuned on LLaMA 65B using an internal Orca-style dataset to enhance instruction following. It excels at answering questions, completing writing tasks, and following complex instructions. Released under a non-commercial CC BY-NC-4.0 license, it targets researchers and developers building open-source LLM applications.

Build a Large Language Model (From Scratch)

Learn to build an LLM from the ground up with hands-on code

This Manning Publications book by Sebastian Raschka guides readers through building a GPT-style large language model from scratch using Python and PyTorch. It covers tokenization, transformer architecture, pre-training, and fine-tuning with clear, step-by-step code examples. The book is designed for ML practitioners and engineers who want a deep, practical understanding of how modern LLMs like ChatGPT actually work under the hood.

Build a Reasoning Model (From Scratch)

Hands-on guide to building reasoning-capable AI models step by step

This Manning Publications book teaches readers how to construct reasoning-focused AI models inspired by systems like OpenAI's o1, covering chain-of-thought training, reinforcement learning from human feedback, and search-augmented inference. It provides practical code implementations alongside the theory to help readers understand how deliberative reasoning emerges in modern LLMs. The book is suited for ML engineers and researchers looking to go beyond standard instruction fine-tuning.

Build an AI Agent (From Scratch)

Practical guide to designing and coding autonomous AI agents

This Manning Publications book provides a step-by-step approach to building autonomous AI agents that can plan, use tools, browse the web, and execute multi-step tasks. It covers agentic frameworks, memory systems, tool calling, and evaluation strategies with hands-on Python implementations. The book is aimed at developers and AI engineers who want to move from passive LLM usage to building production-ready agentic systems.

Context Engineering Guide — Prompt Engineering Guide

In-depth guide to context engineering for LLM applications

The Context Engineering Guide from PromptingGuide.ai provides a thorough overview of techniques for designing and managing the information provided to language models beyond simple prompt writing. It covers retrieval-augmented generation, context window optimization, structured context schemas, and evaluation methods for context quality. The guide is valuable for AI engineers and researchers building sophisticated LLM pipelines who need to go beyond basic prompting.

GPTLocalhost

Run and demo GPT language models entirely on your local machine

GPTLocalhost provides a local interface for running and demoing GPT-based language models without sending data to external servers. It is designed for developers who want to test AI capabilities in a private, offline-friendly environment. Useful for prototyping, privacy-sensitive applications, and evaluating model behavior locally.

Chatbot UI

Open-source self-hostable ChatGPT interface with full customization

Chatbot UI is an open-source, self-hostable web interface for interacting with OpenAI's API, offering a clean ChatGPT-like experience with system prompt customization, model switching, and conversation management. Built by Mckay Wrigley, it is widely used by developers who want full control over their AI chat environment without relying on OpenAI's own interface.

Chat With PDF by Copilot.us

Interact with and extract answers from PDF documents via AI chat

Chat With PDF by Copilot.us allows users to upload PDF files and ask questions, extract summaries, and retrieve specific information through a conversational interface. It handles research papers, contracts, reports, and books with ease. Targeted at students, legal professionals, and business analysts who work with document-heavy workflows.

v0

Generate production-ready UI components from a text prompt

v0 by Vercel is a generative UI tool that converts natural language prompts into React and Tailwind CSS components ready to ship. It supports iterative refinement through chat, exports clean code, and integrates with Next.js projects. Perfect for developers and designers who want to scaffold polished frontends in seconds.

Kilo Code

Open-source AI coding agent for VS Code with deep codebase context

Kilo Code is an open-source AI coding agent extension for VS Code that provides code generation, refactoring, and multi-file editing with full project context awareness. It supports multiple LLM backends and lets developers bring their own API keys for full control. Aimed at developers who want a powerful, customizable AI coding assistant without vendor lock-in.

Debuild

AI-powered low-code tool for building web apps from descriptions

Debuild is an AI-assisted low-code web application builder that generates React components and SQL queries from plain text descriptions. Users describe what they want and Debuild assembles the frontend and backend logic automatically. Geared toward developers and entrepreneurs who want to prototype and launch web apps with minimal manual coding.

tabnine

Privacy-first AI code completion that runs locally or in the cloud

Tabnine is an AI code completion tool that provides whole-line and full-function suggestions across all major languages and IDEs. It can run fully on-premise or locally to keep proprietary code private, making it a popular choice for enterprises with strict data governance requirements. Supports VS Code, JetBrains, Vim, and more with team-specific model personalization.

Amazon CodeWhisperer

Amazon's AI code companion for secure, cloud-aware code generation

Amazon CodeWhisperer is an AI coding assistant from AWS that generates real-time code suggestions and completions directly in popular IDEs including VS Code, JetBrains, and AWS Cloud9. It is trained on Amazon's internal codebase and public code, with built-in security scanning to flag vulnerabilities. Best for developers building on AWS who want code suggestions tuned to AWS APIs and best practices.

OpenAI API

Access GPT-4, DALL-E, and Whisper via a simple REST API

The OpenAI API provides programmatic access to OpenAI's suite of models including GPT-4o, GPT-4, Whisper for speech-to-text, DALL-E for image generation, and embeddings models. Developers can integrate natural language understanding, content generation, and multimodal capabilities into any application. It offers pay-per-token pricing with extensive documentation and SDKs for Python and Node.js.

LLaMA

Meta's efficient foundational LLM released for open research

LLaMA (Large Language Model Meta AI) is a foundational language model released by Meta AI in sizes ranging from 7B to 65B parameters, designed to be more compute-efficient than comparable models. Despite its smaller size, LLaMA outperforms GPT-3 on many benchmarks when fine-tuned. It was released for non-commercial research use and became the base for numerous community fine-tuned models like Alpaca and Vicuna.

Llama 2

Meta's open-source LLM fine-tuned for chat and research

Llama 2 is Meta's second-generation open-source large language model, available in 7B, 13B, and 70B parameter sizes, with both pretrained and fine-tuned chat variants. Unlike the original LLaMA, Llama 2 is released for both research and commercial use under a permissive license. The chat-optimized versions use RLHF alignment and are competitive with many proprietary models on reasoning and dialogue benchmarks.

OpenAI Prompt Engineering Guide

Official OpenAI guide to writing effective prompts for GPT models

OpenAI's Prompt Engineering Guide is official documentation covering best practices and strategies for getting reliable, high-quality outputs from GPT models. It includes techniques like few-shot examples, chain-of-thought prompting, system message design, and instruction clarity. The guide is essential reading for developers and power users building applications on the OpenAI API who want to improve model behavior systematically.

PromptPerfect

Automatically optimize your AI prompts for better model outputs

PromptPerfect is a prompt optimization tool from Jina AI that automatically rewrites and improves user-written prompts for models like GPT-4, Claude, Midjourney, and Stable Diffusion. It analyzes the intent of the original prompt and applies best-practice prompt engineering techniques to enhance clarity, specificity, and output quality. It is useful for non-technical users and developers who want to quickly improve prompts without deep expertise in prompt engineering.

GPT-4 Demo

Discover apps and demos showcasing GPT-4 capabilities across industries

GPT-4 Demo is a directory of applications, experiments, and use cases built using OpenAI's GPT-4 model, organized by industry and task type. It helps developers, entrepreneurs, and researchers explore what has been built with GPT-4 to identify patterns and opportunities. The site complements GPT-3 Demo by specifically highlighting capabilities unlocked by GPT-4's stronger reasoning and multimodal features.

Haystack

Open-source framework for building LLM-powered search pipelines

Haystack is an open-source Python framework by deepset for building production-ready NLP applications, including RAG pipelines, semantic search, and question-answering systems. It supports a wide range of LLMs and document stores, giving ML engineers and developers the composable building blocks to ship robust AI applications.

LlamaIndex

The leading data framework for building LLM-powered applications

LlamaIndex is an open-source data framework that connects custom data sources to large language models for building retrieval-augmented generation (RAG) pipelines and AI agents. It supports ingesting, indexing, and querying documents, databases, and APIs with dozens of integrations. Widely used by developers and enterprises building production LLM applications.

Portkey

AI gateway that unifies LLM providers with reliability and observability

Portkey is an AI gateway that routes requests across 100+ LLM providers with features like load balancing, fallbacks, caching, and rate limiting. It also provides a full observability suite with request logging, cost tracking, and prompt versioning. Built for teams that run LLMs in production and need resilience and cost control.

OpenAI Downtime Monitor

Real-time status tracker for OpenAI API uptime and incidents

OpenAI Downtime Monitor, powered by Portkey, tracks the live availability and latency of OpenAI's API and related services. It shows historical uptime, active incidents, and response time trends across model endpoints. Useful for developers and teams who depend on OpenAI APIs and need instant visibility into service disruptions.

CodeRabbit

AI-powered code review that provides instant, contextual PR feedback

CodeRabbit is an AI code review tool that automatically analyzes pull requests and provides line-by-line feedback on bugs, security issues, style violations, and logic errors. It integrates with GitHub and GitLab and learns from reviewer feedback over time. Suitable for engineering teams who want to accelerate code review and improve code quality.

Callstack.ai PR Reviewer

AI code reviewer specialized for React Native and JavaScript PRs

Callstack.ai PR Reviewer is an AI-powered pull request review tool built by the React Native experts at Callstack. It provides automated, contextual feedback on JavaScript and React Native code, covering performance, best practices, and React-specific patterns. Tailored for React Native teams who want domain-specific AI review beyond generic linting.

Calmo

AI-powered customer support automation for lean support teams

Calmo is an AI customer support tool that automates responses to common inquiries using your existing knowledge base and documentation. It handles ticket deflection, drafts replies for agent review, and escalates complex issues to humans. Designed for small and mid-sized teams looking to scale support quality without growing headcount.

Amazon Q Developer CLI

AI-powered CLI assistant for AWS development and cloud tasks

Amazon Q Developer CLI brings AWS's generative AI assistant directly into the terminal, enabling developers to get code suggestions, explain shell commands, and automate AWS tasks through natural language. It integrates with the AWS CLI and supports workflows like infrastructure setup, debugging, and service configuration. Built for developers and cloud engineers working in AWS environments.

Agenta

Open-source LLMOps platform for prompt engineering and evaluation

Agenta is an open-source platform for building, versioning, and evaluating LLM applications with a focus on prompt engineering workflows. It provides a playground for testing prompts, A/B comparison, human evaluation tools, and deployment pipelines. Suited for AI engineers and product teams who need a structured approach to iterating on LLM-powered features.

Gemini CLI

Google's open-source AI agent for coding tasks in the terminal

Gemini CLI is an open-source command-line AI agent by Google that uses Gemini models to assist with coding, file editing, and agentic tasks directly in the terminal. It connects to Google Search for grounding and supports tool use for real-world actions. Aimed at developers who want a capable, free, open-source terminal AI assistant.

Devin

The first fully autonomous AI software engineer for real tasks

Devin by Cognition AI is an autonomous AI software engineer that can plan, code, debug, and deploy full projects end-to-end inside its own sandboxed environment with a browser, terminal, and editor. It tackles multi-step engineering tasks from a single natural language specification. Designed for engineering teams who want to delegate entire coding tasks to an AI agent.

RunThisLLM

Find the right LLM setup and run it locally in minutes

RunThisLLM helps users discover and configure local LLM setups by recommending models and hardware configurations based on their specific machine specs. It simplifies the decision of which model to run and how, reducing setup friction for newcomers to local AI. Aimed at developers and curious users who want to get a local model running fast.

LLM

Run and log prompts to any LLM from the command line

LLM is a CLI tool and Python library by Simon Willison (Datasette) for running prompts against OpenAI, Anthropic, Gemini, and local models from the terminal. It logs every prompt and response to a local SQLite database and supports plugins for additional model providers. Ideal for developers and researchers who want scriptable, auditable LLM access.

OpenAI Playground

Interactively test and tune OpenAI models in your browser

OpenAI Playground is a web-based interface for experimenting with GPT-4, o1, and other OpenAI models in chat, completion, and assistants modes. Users can adjust system prompts, temperature, and token limits in real time and compare model outputs. It's the go-to sandbox for developers prototyping prompts before embedding them in applications.

Unsloth

Fine-tune LLMs up to 5x faster with 70% less VRAM usage

Unsloth is an open-source library that dramatically accelerates LLM fine-tuning by rewriting key CUDA kernels in Triton. It supports QLoRA and LoRA training for Llama, Mistral, Gemma, and other models with minimal code changes. Targeted at ML engineers and researchers who want to fine-tune large models on consumer or budget GPUs.

Gitingest

Turn any GitHub repo into a single LLM-ready text digest

Gitingest converts a GitHub repository URL into a clean, structured text file optimized for pasting into LLM context windows. It strips noise, respects .gitignore, and lets users filter by file type or directory. Handy for developers who want to give an AI assistant full codebase context with a single URL.

Cursor

AI-first code editor built on VS Code with deep model integration

Cursor is a fork of VS Code that embeds powerful AI features including multi-file editing, codebase-wide chat, and an AI agent that can autonomously complete tasks. It supports GPT-4 and Claude models, autocomplete, and inline diff review. Popular among professional developers who want AI assistance tightly integrated into a familiar editor.

Copilot

Microsoft's AI companion powered by GPT-4 across all products

Microsoft Copilot is an AI assistant integrated across Microsoft's ecosystem including Windows, Edge, Microsoft 365, and Bing. Powered by OpenAI's GPT-4, it helps with writing, research, image generation, coding, and task automation. Available for free with optional paid plans for enhanced productivity features.

Interviews Chat

Ace your next job interview with real-time AI coaching and feedback

Interviews Chat provides AI-powered mock interview practice with personalized feedback on answers, tone, and structure. Job seekers can rehearse role-specific questions, receive improvement tips, and build confidence before facing real interviewers across any industry.

Scale Spellbook

Build, compare, and deploy LLM apps with enterprise-grade tooling

Scale Spellbook is a prompt engineering and LLM evaluation platform by Scale AI that helps teams design, test, and deploy large language model applications. It offers side-by-side model comparisons, versioned prompt management, and human-in-the-loop evaluation suited for enterprise AI teams.

google.github.io/adk-docs/a2a/

Google's Agent-to-Agent protocol for interoperable AI agent networks

The Agent-to-Agent (A2A) protocol is Google's open specification, part of the Agent Development Kit (ADK), that defines how AI agents discover, communicate, and delegate tasks to one another across different frameworks and vendors. It complements the Model Context Protocol by focusing on agent interoperability rather than tool connectivity, enabling complex multi-agent orchestration. The protocol is aimed at developers building enterprise-grade agentic systems that span multiple specialized agents.

Tura

New This Month

Open-source local coding agent with macro execution

Tura is an open-source local coding agent for developers. Its macro execution layer combines inspect, edit, build, test, lint and media-reading steps to reduce model round trips. The repository includes a reproducible 60-task DeepSWE benchmark. Disclosure: I maintain Tura; this submission was AI-assisted and reviewed against the source and benchmark records.

blyft

New This Month

Build apps, websites, logos and launch assets with one AI prompt.

Blyft is an AI vibe coding platform that builds web apps and websites, then generates all the branding and launch assets for your product.

Pawse

Your virtual pet which reacts to your work.

Pick a cat, dog, panda, or hamster. A free pixel-art desktop pet (and mascot) that follows your cursor, reacts to your typing, and naps while your AI agent works. macOS & Windows.

AI Test Case Generator Pro

Turn requirements, Jira stories, and API notes into QA test cases in minutes.

AI Test Case Generator Pro is a paid prompt and template pack for QA engineers, product managers, developers, and SaaS teams. It helps turn messy requirements, Jira stories, API notes, and bug reports into structured test cases, BDD scenarios, edge cases, regression checks, and CSV-ready QA sheets. It is lightweight and buyer-owned: teams use the templates to create a stronger first draft, then review and adapt the output before importing it into their own QA workflow.

Buildwhat

AI-generated startup ideas from tech discussions

About: BuildWhat is a platform that uses artificial intelligence to analyze technology discussions and surface potential startup ideas. It scans posts and conversations, extracting insights and transforming them into structured business concepts. Each idea is evaluated based on factors such as problem severity, market size, timing, competition, and defensibility. The platform helps users quickly identify promising opportunities without manually filtering large volumes of content. By focusing on real-world discussions, it highlights emerging needs and gaps in the market. BuildWhat is designed for founders, indie hackers, and builders who want a steady stream of data-informed ideas to explore, validate, or develop into products. Problems: Finding validated startup ideas from noisy tech discussions is time-consuming. solution: AI analyzes tech posts daily to extract and score actionable startup ideas. Target Audience: Indie hackers, founders, and product builders Main Features: Daily idea generation AI-scored ideas Trend-based insights Discussion analysis Idea ranking system User Case Sarah Zhang - Full Stack Engineer, Beijing "BuildWhat's AI assistant is really powerful! It saved me a lot of time, and the code quality has significantly improved. Highly recommended to all developers." Li Wei - Entrepreneur, Shanghai "As a startup, we need rapid iteration. BuildWhat helped us complete our MVP in just a few weeks, amazing!" Michael Tan - Mobile Developer, Singapore "Cross-platform support allows me to build apps for both iOS and Android simultaneously. Greatly reduces workload, highly recommended!" Emma Park - Product Engineer, Seoul "The workspace flow feels fast and focused. We moved from prototype to launchable product without the usual setup drag." David Lin - Indie Hacker, Taipei "MCP and workflow automation cut repetitive ops work for my solo projects. It feels like having a sharp technical copilot." Alicia Gomez - Engineering Lead, Barcelona "The combination of model control, workspace context, and deployment flow makes the whole team move with less friction."

Roblox GUI Maker

Free AI Roblox GUI maker for Roblox Studio UI layouts and Lua starter code.

Roblox GUI Maker helps Roblox Studio creators generate ScreenGui layouts for menus, HUDs, inventory screens, shop panels, settings panels, and other game UI from a prompt. It provides a Roblox-style preview plus Lua starter code that developers can copy into Studio and customize.

Lians

New This Month

Reconstruct what AI knew, did, and why at decision time

Lians is the system of record for AI in regulated workflows. It preserves exact source, prompt, policy, permission, model, and tool versions so teams can reconstruct agent decisions after the underlying facts change. Built for financial research, risk, compliance, and other evidence-heavy AI workflows.