Home / Open Source
AI Open Source Ranking
Synced from GitHub in real time — newly added, recent updates, total stars and star growth.
Newly Added Recently updated Stars Star growth
CategoryAll categoriesTTSAgentFine TuningDBCrawlerSearch & RAGMCPPlatformApplicationDeploy & InferenceFrameworkskillPlugins
#ProjectLangNewly Added
01
nanobrowserOpen-source Chrome extension that uses multi-agent AI to automate web browsing tasks locally and for free.Agent
mempalaceLocal-first AI memory system that stores conversation history verbatim and retrieves it with fast, structured semantic search.Agent
skillsOpen-source CLI that lets AI agents control real browsers, bypass anti-bot defenses, and hand off to humans when stuck.Crawler
reverse-skillA rule-based skills router that guides AI agents through reverse engineering, penetration testing, and CTF workflows with the right tools and methodology.skill
Financial-APIHiThink's official A-share financial data service, unified across REST API, CLI, Python SDK, MCP, and Agent Skill for AI agents and quant researchers.Platform
Prompt-Engineering-GuideAn open-source guide consolidating research, techniques, and examples for effectively prompting large language models.skill
llm-appReady-to-run Docker templates for building RAG pipelines and enterprise search apps that stay live-synced with your data sources.Search & RAG
langgraphLangGraph is a low-level orchestration framework for building resilient, stateful, long-running AI agents.Agent
langchainLangChain is an open-source Python framework for building LLM-powered applications, RAG pipelines, and autonomous agents with a unified interface across model providers.Framework
cavemanOpen-source skill and local proxy that compress AI coding agents' inputs and outputs to cut token usage while preserving exact code and logs.skill
piPi is a self-extensible, terminal-based coding agent framework with a unified multi-provider LLM API.Agent
superpowersA composable skills library that gives AI coding agents a disciplined, test-driven software development methodology.skill
OfficeCLIOfficeCLI is a single-binary command-line tool that lets AI agents create, read, and modify Word, Excel, and PowerPoint documents with built-in visual rendering.Application
deepseek-harnessAn open-source, plugin-based agent framework from DeepSeek AI where models, tools, sandboxes, storage, and the UI are all swappable Cordis plugins with full session traceability.Agent
TencentDB-Agent-MemoryA team-level memory management system that turns agent conversations, docs, and code into reusable Chat Memory, Skills, Wiki, and CodeGraph assets.Agent
ponytailA portable skill/ruleset for AI coding agents that enforces a decision ladder to minimize generated code while preserving safety and accessibility.skill
anydocA fast Rust library that converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF files into clean, consistent Markdown.Crawler
opencodexA local proxy that routes any LLM provider through Codex, Claude Code, Claude Desktop, and Grok Build with full feature parity.Deploy & Inference
gatewayOpen-source AI gateway that routes requests to 1,600+ LLMs across 50+ providers through one unified API, with built-in fallbacks, retries, guardrails, and cost controls.Deploy & Inference
new-apiAn open-source, self-hosted LLM gateway that unifies OpenAI, Claude, Gemini and other AI providers behind one API with billing, routing and auth.Deploy & Inference
‹12345…21›