Awesome Opensource Ai

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.

The Security Toolkit for LLM Interactions

Bonsai Demo

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

🦜💬 Web app for interacting with any LangGraph agent (PY & TS) via a chat interface.

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

Multi-framework streaming Markdown renderers for AI apps: Vue/Nuxt, React/Next.js, Svelte, and Angular, with Mermaid, KaTeX, stream-diffs code blocks, safe HTML, and low-jitter updates.

The pretty much "official" DSPy framework for Typescript

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

Community maintained hardware plugin for vLLM on Ascend

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.

SDG is a specialized framework designed to generate high-quality structured tabular data.

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

Research project. A Memory solution for users, teams, and applications.

Vim plugin for LLM-assisted code/text completion

You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub Copilot/Kiro/Z.AI/MiniMax/Kimi(300+ models, 200+ LLM providers, free models no auth) Build your AI company with multiple teams

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that interact with your data and UI.

Manages Unified Access to Generative AI Services built on Envoy Gateway

ContextGem: Effortless LLM extraction from documents

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

Synthetic data curation for post-training and structured data extraction

Automated Machine Learning on Kubernetes

A fast and lightweight framework for creating decentralized agents with ease.

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Fast Multimodal LLM on Mobile Devices

The LLM Anti-Framework

The open document intelligence platform for builders and hackers - DMS for the agentic world

💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.

🌎💪 BrowserGym, a Gym environment for web task automation

Ground truth layer for humans and AI agents working together. Version control for knowledge.

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

AI-powered code assistant for Vim. OpenAI and ChatGPT plugin for Vim and Neovim.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana & Splunk.

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

Self-Programming AI Agent Framework. Agents create and refine their own workflows.

Intent as Code | the workflow language for AI. One file, 4 verbs, one Rust binary. Local-first, any model, AGPL-3.0. 🦋

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas and agent harnesses powering today's AI products. Captured with OrcaReplay.

AI agent for QGIS: ask in plain English and it finds the data, runs the analysis and builds the map in your open project. One click undoes anything it changed. QGIS plugin by TerraLab, free tier, no card.