Open Source Developer tools AI tools

Gemini CLI is a terminal-based AI agent that lever...

Gemini CLI is a terminal-based AI agent that leverages Gemini's multimodal capabilities to automate coding tasks, manage codebases, and streamline GitHub operations. It enables developers to generate content, handle version control, and boost productivity through high-level tool integrations.

Mistral AI offers developers a platform for buildi...

Mistral AI offers developers a platform for building cutting-edge generative AI models with a focus on performance and customization. Their models excel in reasoning tasks and benchmarks, providing flexible deployment options across infrastructures.

Img2Prompt is an AI tool that generates text promp...

Img2Prompt is an AI tool that generates text prompts from images and provides a public API for image captioning and prompt-based image generation. It can run on personal hardware or cloud platforms.

Nimbalyst is an open-source visual workspace facil...

Nimbalyst is an open-source visual workspace facilitating seamless collaboration with AI coding agents like Claude Code and Codex. It provides a centralized environment for managing agent sessions, tasks, and files through a visual editor and real-time AI diff review.

Cognee is an open-source agent memory platform tha...

Cognee is an open-source agent memory platform that captures context, builds graph and vector memory, and enables persistent, searchable recall across sessions via an SDK, memory API, connectors (S3, Slack, Notion, Drive) and governance controls.

Codexbar integrates with Cursor to centralize sess...

Codexbar integrates with Cursor to centralize session-based authentication and API usage reporting, surfacing per-model and billing-window metrics, provider cost estimates, account selection, storage footprint, and CLI/manual login options for developer, DevOps, and security teams.

ecc.tools converts repository history into reusabl...

ecc.tools converts repository history into reusable skills, agents, and harnesses, providing a skills catalog, GitHub app for repo-native automation, continuous learning, security scanning (AgentShield), TDD/security enforcers, and configurable installs for CI/CD workflows.

Lemonade is a self-hosted local AI platform offeri...

Lemonade is a self-hosted local AI platform offering GUI, CLI, REST API and SDKs to host and run multimodal models (text, image, code, speech), manage model lifecycle, benchmark inference, deploy on-prem agents, and keep data local.

Helicone is an open-source platform for LLM observ...

Helicone is an open-source platform for LLM observability, featuring logging, monitoring, and debugging tools. It supports high request processing, offers instant analytics, and enables integration with major AI services, while prioritizing security and community collaboration.

Chainlit is an open-source framework for building ...

Chainlit is an open-source framework for building conversational AI applications that supports multimodal interactions, integrates with authentication providers, offers a prompt playground for optimization, and ensures data privacy through a self-hosted platform for managing conversational data.

APIPark is an open-source AI gateway and API porta...

APIPark is an open-source AI gateway and API portal that simplifies AI model management, integration, and deployment, offering unified API formatting, lifecycle management, and secure multi-tenant support for efficient AI usage.

Emdash.sh is an open-source agentic development en...

Emdash.sh is an open-source agentic development environment that orchestrates coding agents across isolated git worktrees for parallel execution and best-N experimentation. It provides a unified dashboard with built-in review tools and integrations to manage, compare, and ship agent-generated code without switching contexts.

Foundry Local runs AI models on-device using ONNX ...

Foundry Local runs AI models on-device using ONNX Runtime (CPU/GPU/NPU) to keep data local, offering an OpenAI-compatible API, Python/JS/C#/Rust SDKs, a model hub, and CLI tools for edge and enterprise deployments.

claude-dev.tools is a session analysis and debuggi...

claude-dev.tools is a session analysis and debugging suite for Claude that reconstructs full session context and provides detailed token attribution across all components. It offers local and remote log inspection, execution trace visualization, and security monitoring through a self-hosted, open-source desktop application.

cli-anything hub is a registry and marketplace for...

cli-anything hub is a registry and marketplace for agent-native CLIs and skills, indexing dozens of tools across 31+ categories. It provides a unified CLI for discovery, installation, inspection, and integration tooling for agent developers.

PinMe provides instant static-site deployment via ...

PinMe provides instant static-site deployment via an npm CLI or browser drag-and-drop, with GitHub integration, upload history, and basic file management. Sites publish to IPFS for peer-to-peer distribution and cryptographic verification.

Otari is an open-source AI gateway and control pla...

Otari is an open-source AI gateway and control plane that unifies access to 40+ LLM providers via a single endpoint, offering per-workspace routing, automatic failover, budget and token enforcement, centralized API key management, audit trails, and SDKs.

Open-source, fast, network-connected, differentiab...

Open-source, fast, network-connected, differentiable tensor library for TypeScript (and JavaScript).

A command-line HTTP client with features such as s...

A command-line HTTP client with features such as syntax highlighting, JSON support, automatic authentication, API testing, network request debugging, and custom tool building. Available for Windows, Mac, and Linux.

Get answers for CLI commands from GPT3 directly in...

Get answers for CLI commands from GPT3 directly in the terminal using AI-powered CLI tool.

Explain the purpose and benefits of using sagify f...

Explain the purpose and benefits of using sagify for generating long descriptions.

ComfyUI is a powerful and modular stable diffusion...

ComfyUI is a powerful and modular stable diffusion GUI with a graph/nodes interface that lets you design and execute advanced stable diffusion pipelines using a flowchart-based interface.

LLM-answer-engine is an advanced answer engine lev...

LLM-answer-engine is an advanced answer engine leveraging Groq, Mixtral, Langchain.JS, Brave Search, Serper API, and OpenAI to provide sources, answers, images, videos, and follow-up questions efficiently. It offers an opensource Perplexity alternative.

OpenUI simplifies UI component creation by allowin...

OpenUI simplifies UI component creation by allowing instant visualization of changes. It supports HTML to React, Svelte, and Web Components conversion, aiding in rapid prototyping and testing. Developed by W&B, it's part of their next-gen tooling for LLM-based applications.

KoboldCpp is a versatile AI text-generation tool t...

KoboldCpp is a versatile AI text-generation tool that supports various GGML and GGUF models with an intuitive UI, native image generation, and enhanced performance via CUDA and CLBlast acceleration.

The text-generation-webui is a Gradio-based web UI...

The text-generation-webui is a Gradio-based web UI for Large Language Models, supporting various backends and multiple interface modes. It allows quick model switching, extension integration, and dynamic LoRA loading for custom training.

GraphRAG by Microsoft is an advanced graph-based s...

GraphRAG by Microsoft is an advanced graph-based system for extracting structured data from unstructured text using large language models. It improves reasoning over private data and offers a user-friendly experience with Azure resources.

exllama is a memory-efficient tool for executing H...

exllama is a memory-efficient tool for executing Hugging Face transformers with the LLaMA models using quantized weights, enabling high-performance NLP tasks on modern GPUs while minimizing memory usage and supporting various hardware configurations.

VLLM is a high-throughput, memory-efficient infere...

VLLM is a high-throughput, memory-efficient inference engine for Large Language Models, enabling faster responses and effective memory management. It supports multi-node configurations for scalability and offers robust documentation for seamless integration into workflows.

Llama.cpp is an open-source tool for efficient inf...

Llama.cpp is an open-source tool for efficient inference of large language models. Run open source LLM models locally everywhere.