function: agent-framework
2430 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| TheAiSingularity/graphrag-local-ollama A local adaptation of Microsoft's GraphRAG that runs LLM and embedding extraction entirely through Ollama models like llama3, mistral, gemm… | 60 | 1108 | active |
| dp-archive/archive Skill Compose is an open-source agent builder and runtime platform for creating skill-powered AI agents, written in Python. It deliberately… | 60 | 1105 | active |
| canwhite/Krebs Krebs is a self-hosted AI gateway with a general-purpose agent focused on attention management. It provides multi-turn dialogue with tool e… | 60 | 1104 | active |
| KroMiose/nekro-agent NekroAgent is a cross-platform AI agent framework for multi-user chat scenarios that generates and executes code in sandboxed containers, w… | 90 | 1103 | active |
| moltlaunch/cashclaw CashClaw is an autonomous AI agent that connects to the Moltlaunch onchain marketplace, where it evaluates tasks, quotes prices, executes w… | 47 | 1102 | active |
| Onelevenvy/flock Flock is a cross-platform desktop multi-agent harness built with Rust, Tauri, and React, powered by the langgraph-rust engine. It provides … | 82 | 1101 | active |
| agentrq/agentrq AgentRQ is a self-hosted, human-in-the-loop task management and collaboration platform for AI agents, built around the Model Context Protoc… | 82 | 1101 | active |
| openresponses/openresponses Open Responses is an open-source specification for multi-provider, interoperable LLM interfaces modeled on the OpenAI Responses API, defini… | 57 | 1100 | active |
| BytedTsinghua-SIA/MemAgent MemAgent is a reinforcement-learning framework for training LLM agents that process arbitrarily long contexts via a memory mechanism within… | 55 | 1100 | active |
| agentlas-ai/Agentlas-OS Agentlas OS (with the Hephaestus engine) is an open-source agent framework that lets users create portable AI agents from plain-language re… | 77 | 1099 | active |
| snarktank/clawchief Clawchief is an opinionated starter kit that turns OpenClaw into a founder/chief-of-staff operating system. It provides markdown-based task… | 64 | 1099 | active |
| zjunlp/LightMem LightMem is a lightweight Python framework for adding long-term memory to LLM applications and AI agents, providing memory storage, retriev… | 64 | 1099 | active |
| alibaba-flyai/flyai-skill FlyAI is an agent skill that connects Claude Code, OpenClaw, and other skill-compatible AI agents to Fliggy's travel platform for searching… | 59 | 1099 | active |
| Gen-Verse/LatentMAS LatentMAS is a training-free multi-agent reasoning framework that lets LLM agents collaborate in continuous latent space by passing hidden-… | 56 | 1099 | active |
| xiaobright/dsh-anchored-standard A community plugin providing DeepSeek Harness (DSH) agent presets that bootstrap a session with a minimal tool schema and then promote to a… | 57 | 3775 | maintenance |
| Rath-Team/OpenRath OpenRath is a PyTorch-like Python framework for building dynamic multi-agent and multi-session workflows. It models runtime state as explic… | 78 | 1097 | active |
| withkynam/vibecode-pro-max-kit A spec-driven coding harness that gives AI coding agents (Claude Code, Codex, Cursor, etc.) a plan-first workflow with gated phases, self-h… | 72 | 1096 | active |
| paean-ai/deeptide DeepTide is an AI coding agent tuned for DeepSeek models, shipped as a Swift-native macOS app plus cross-platform terminal CLIs (TypeScript… | 58 | 1096 | active |
| ChesterRa/cccc CCCC is a Python-based multi-agent orchestrator that coordinates coding agents (Claude Code, Codex CLI, ChatGPT Web, Gemini CLI, and 13+ ot… | 81 | 1094 | active |
| bubblelabai/BubbleLab Bubble Lab is an open-core workflow engine written in TypeScript that powers the Bubble Lab Slack-native AI operator platform. It can be ru… | 53 | 1094 | active |
| Emiyaaaaa/HiveMind AgentFlow (repo HiveMind) is a Python-first runtime layer for multi-agent systems that adds persistent run state, ordered step/message/tool… | 62 | 1092 | active |
| FANzR-arch/Numerologist_skills An engineering framework of AI skills for Chinese metaphysics (Qimen Dunjia, Ziwei Doushu, BaZi) that reduces LLM hallucinations by enforci… | 57 | 1092 | active |
| TencentCloudBase/CloudBase-AI-Toolkit CloudBase AI Toolkit is Tencent Cloud's integration layer connecting AI coding tools (Cursor, Claude Code, Codex, etc.) to the CloudBase ba… | 82 | 1090 | active |
| hinthornw/trustcall A Python library that improves LLM tool calling reliability by having models generate JSON patch operations instead of full JSON blobs. It … | 38 | 1089 | active |
| wenge-research/x-agent X-Agent (智川) is an open-source, self-hosted enterprise agent development platform by Wenge that lets users build AI applications with zero … | 34 | 1088 | active |
| xuzhougeng/wisp-science Wisp Science is an open-source, local-first desktop AI research workbench that combines an LLM agent with persistent Python/R kernels, MCP-… | 81 | 1087 | active |
| amruth-sn/kong Kong is an LLM-orchestrated reverse engineering CLI that plugs AI into Ghidra's analysis engine to recover function names, types, and struc… | 63 | 1087 | active |
| RinDig/Interpretable-Context-Methodology Interpretable Context Methodology (ICM) is a Python-based methodology that uses folder structure as agent architecture, replacing framework… | 57 | 1087 | active |
| vercel-labs/eve-software-factory-template Foreman is a template for an 'eve Software Factory' that runs AI agents across the development loop: a classifier triages tasks from GitHub… | 57 | 1087 | active |
| langchain-ai/agent-inbox Agent Inbox is a web-based inbox UI for reviewing and responding to human-in-the-loop interrupts raised by LangGraph agents. It connects to… | 67 | 1086 | active |
| piotrostr/listen Listen is a Rust toolkit and framework for algorithmic trading on Solana, evolving into a framework for AI-driven crosschain portfolio mana… | 47 | 1085 | active |
| xataio/agent Xata Agent is an open-source AI agent that acts as a PostgreSQL expert, monitoring database logs and metrics, diagnosing root causes of iss… | 10 | 1085 | active |
| LiuMengxuan04/MiniCode MiniCode is a lightweight terminal-based AI coding assistant that implements a Claude Code-like agent loop with tool calling, diff review, … | 59 | 1084 | active |
| StreetLamb/tribe Tribe AI is a low-code web application for rapidly building and coordinating multi-agent teams using drag-and-drop, built on LangChain and … | 49 | 1084 | active |
| andrepimenta/claude-code-chat A VS Code extension that provides a graphical chat interface for Claude Code, replacing terminal-based interaction with a visual UI inside … | 77 | 1081 | active |
| digitalinnovationone/dio-agent DIO Agent is an AI study mentor created by Digital Innovation One (DIO) that guides learners through bootcamps, courses, and coding challen… | 55 | 1081 | active |
| GradientHQ/symphony-coord Symphony-Coord is a decentralized multi-agent framework that treats agent selection as an online multi-armed bandit problem, allowing roles… | 54 | 1080 | active |
| sipyourdrink-ltd/bernstein Bernstein is a deterministic Python scheduler that orchestrates CLI coding agents (Claude Code, Codex, Gemini CLI, Aider, and 40+ more) run… | 78 | 1079 | active |
| smixs/pohuy A prompt/skill package that makes AI agents respond in idiomatic Russian profanity, compressing verbose explanations into terse, expressive… | 78 | 1078 | active |
| spring-ai-alibaba/Lynxe Lynxe (formerly JManus) is a Java-based, code-free 'Prompt Programming' studio implementing a Manus-style multi-agent system with high exec… | 76 | 1077 | active |
| Pokee-AI/PokeeResearchOSS An open-source repository for Pokee's 7B-parameter DeepResearch agent that performs multi-turn web search and content reading to answer com… | 38 | 1076 | active |
| zubair-trabzada/ai-sales-team-claude A collection of 14 Claude Code skills and 5 parallel agents that turn Claude Code into an AI-powered sales team. It researches prospects, q… | 48 | 1075 | active |
| lee-to/ai-factory AI Factory is an npm-distributed CLI that bootstraps an AI-powered development environment in any project, installing skills, configuring M… | 82 | 1074 | active |
| leezythu/maoxuan-skill A Claude Code skill package that distills the cognitive frameworks from Mao Zedong's Selected Works (e.g., contradiction analysis, united f… | 58 | 1073 | active |
| OranAi-Ltd/oransim Oransim is an open-source causal digital twin engine for marketing, simulating a large virtual consumer society with LLM-backed personas to… | 56 | 1073 | active |
| XiaoLuoLYG/GOD GOD (Govern, Observe, Direct) is a real-time control room for inspecting and steering societies of LLM-powered agents, letting operators pa… | 74 | 1072 | active |
| titanwings/ex-skill A Python tool that generates Claude Code / OpenClaw agent 'skills' capturing a specific person's texting persona from chat history (WeChat,… | 62 | 1072 | active |
| jjsantos01/qgis_mcp A Model Context Protocol integration that lets LLMs like Claude control QGIS Desktop via a socket-based QGIS plugin and an MCP server. It s… | 40 | 1072 | active |
| trendy-design/llmchat LLMChat is a privacy-focused AI chat platform built with Next.js and TypeScript that provides a unified interface for chatting with multipl… | 24 | 1072 | active |
| nvk/llm-wiki A plugin that lets AI agents (Claude Code, OpenAI Codex, OpenCode, portable agents) compile and maintain LLM-curated knowledge bases as pla… | 77 | 1070 | active |
| tryAGI/LangChain LangChain .NET is a C#/.NET implementation of the LangChain framework for building LLM-powered applications through composability. It provi… | 65 | 1070 | active |
| NanmiCoder/dsh-agent-teams A DeepSeek Harness plugin that turns a single session into a captain coordinating durable sub-agents as a team. It provides dependency-awar… | 79 | 1067 | active |
| dynamiq-ai/dynamiq Dynamiq is an open-source Python orchestration framework for building agentic AI and LLM applications, covering agents, RAG pipelines, work… | 85 | 1066 | active |
| metaskills/experts Experts.js is a JavaScript library that simplifies creating and deploying OpenAI Assistants via the Assistants API, hiding Run object manag… | 24 | 1065 | active |
| openops-cloud/openops OpenOps is an open-source, no-code FinOps automation platform that helps organizations reduce cloud costs through customizable workflows fo… | 82 | 1064 | active |
| op7418/guizang-material-illustration A Claude Code / Codex agent skill that generates material-style illustrations with Chinese labels for articles, notes, charts, and teaching… | 54 | 1064 | active |
| Lazarus-AI/clearwing Clearwing is a dual-mode autonomous offensive-security tool that combines a network-pentest ReAct agent with an LLM-driven source-code vuln… | 63 | 1063 | active |
| MayDay-wpf/snow-cli Snow CLI is a terminal-based AI coding agent written in TypeScript that can read, write, and refactor code directly from the command line. … | 80 | 1062 | active |
| rogue-security/rogue Rogue is an open-source AI agent evaluator and red teaming platform that stress-tests agents against business policies and simulated advers… | 78 | 1058 | active |
| viticci/shortcuts-playground-plugin Shortcuts Playground is a plugin for Claude Code and Codex that generates Apple Shortcuts from natural language descriptions. It ships a kn… | 72 | 1058 | active |
| ufy2024/AuC AuC (Agents-ufy-Core) is a Python single-agent framework built on asyncio with a pluggable ReAct reasoning loop, LLM adapters, tiered tool … | 56 | 1058 | active |
| Fullive-AI/Anima Anima is an open-source Agent OS that gives home hardware perceptive, decision-making, and learning AI capabilities by connecting devices t… | 58 | 1056 | active |
| XYZ-AI-Lab/axrl AxisRL is an agentic reinforcement learning post-training framework for large language models, built on SGLang for high-throughput rollout … | 55 | 1056 | active |
| vigolium/vigolium Vigolium is a high-fidelity web vulnerability scanner written in Go that combines deterministic multi-phase scanning (317 modules for conte… | 82 | 1055 | active |
| microsoft/Agents The Microsoft 365 Agents SDK is a multichannel SDK for building full-stack, trusted agents deployable to Microsoft 365 Copilot, Teams, Copi… | 67 | 1055 | active |
| lennybase/browsernode Browsernode is a TypeScript implementation of Browser-use that lets LLM-powered AI agents control a web browser via Playwright. It provides… | 34 | 1055 | active |
| asklokesh/loki-mode Loki Mode is a spec-driven autonomous SDLC framework that turns a PRD, GitHub issue, OpenAPI spec, or one-line brief into a deployed applic… | 79 | 1054 | active |
| huohua325/Memslides MemSlides is a hierarchical memory-driven agent framework for generating and revising personalized slide decks. It separates long-term memo… | 67 | 1054 | active |
| OpenLAIR/dr-claw Dr. Claw is an open-source, model-agnostic AI research assistant that provides a desktop and mobile UI for Claude Code, Cursor CLI, Codex, … | 82 | 1050 | active |
| huytieu/COG-second-brain COG is a self-evolving second brain built from markdown files, Git, and AI agent skills, with 33 skills, 10 agents (6 workers plus 4 read-o… | 83 | 1049 | active |
| shyamsaktawat/OpenAlpha_Evolve OpenAlpha_Evolve is an open-source Python framework inspired by DeepMind's AlphaEvolve that uses LLMs to iteratively generate, test, and ev… | 30 | 1049 | active |
| CRui5in/paper-ppt-agent A self-hosted web application that uses a multi-agent AI pipeline (Strategist, Executor, Critic) to convert academic papers from PDF or LaT… | 79 | 1048 | active |
| mikiarlo3/ai-copywriter A portable Markdown-based agent skill that writes marketing copy (headlines, descriptions, microcopy, subject lines) with a human tone whil… | 55 | 1048 | active |
| wu-yc/LabClaw LabClaw is a modular library of 240 SKILL.md agent skills for biomedical AI research, covering biology, drug discovery, medicine, data scie… | 48 | 1048 | active |
| RUC-NLPIR/Arbor Arbor is a generalist autonomous research agent that takes a benchmark and a goal, then proposes hypotheses, edits code, and runs real expe… | 78 | 1047 | active |
| banteg/takopi Takopi is a Python CLI tool that bridges coding agent CLIs (Codex, Claude Code, OpenCode, Pi) to Telegram, letting you send tasks from your… | 71 | 1047 | active |
| kreneskyp/ix IX is a self-hosted platform for designing, running, and scaling autonomous and semi-autonomous LLM-powered agents and workflows. It includ… | 48 | 1045 | active |
| vstorm-co/pydantic-deepagents Pydantic Deep Agents is an open-source, self-hosted terminal AI assistant (a Claude Code alternative) plus the Python framework behind it, … | 78 | 1044 | active |
| LocoreMind/locoagent LocoAgent is an AI-powered social media agent that autonomously operates real accounts through genuine browser automation via Chrome DevToo… | 72 | 1043 | active |
| octos-org/octos Octos is a self-hosted AI agent runtime that runs a personal AI assistant on your own machine, connecting to providers like Anthropic, Open… | 80 | 1041 | active |
| wrtnlabs/agentica Agentica is a TypeScript agentic AI framework specialized in LLM function calling, enhanced by compiler-driven validation via typia. Agents… | 71 | 1041 | active |
| jonwiggins/optio Optio is a self-hosted workflow orchestration platform for AI coding agents that runs on Kubernetes. It drives tickets from GitHub, Linear,… | 74 | 1040 | active |
| star23/Day1Global-Skills A collection of investment analysis skills for AI agents, covering tech earnings deep dives, Buffett-style value investing, US market senti… | 59 | 1040 | active |
| metauto-ai/GPTSwarm GPTSwarm is a Python library for building LLM-based agents as computational graphs, with modules for agent graphs, memory, LLM backends, an… | 55 | 1040 | active |
| smallcloudai/refact Refact is an open-source, self-hosted AI coding agent written in Rust that plans and executes engineering tasks end-to-end from your IDE, w… | 10 | 3540 | maintenance |
| vercel-labs/tersa Tersa is an open-source visual AI playground built as a Next.js web application where users drag, drop, and connect nodes on a canvas to bu… | 64 | 1039 | active |
| D2I-CUHKSZ/MicroWorld MicroWorld is a lightweight Python engine that turns multi-modal event materials (documents, images, videos, graph signals) into structured… | 53 | 1039 | active |
| LeoYeAI/openclaw-marketing-skills A collection of 37 battle-tested marketing skills (prompt packs) for OpenClaw AI agents, covering CRO, copywriting, SEO, paid ads, email, g… | 53 | 1039 | active |
| numman-ali/n-skills A curated marketplace of reusable AI agent skills in the universal SKILL.md format, installable via Claude Code plugins or the openskills i… | 68 | 1038 | active |
| TIGER-AI-Lab/verl-tool VerlTool is a unified, extensible framework built on verl for training LLM agents with tool use via reinforcement learning. It decouples ac… | 66 | 1036 | active |
| ZhangJinHaHaHa/AgentLens AgentLens is a trust-first AI Agent marketplace and workspace where users can discover, compare, and rent task-specific Agents backed by sm… | 59 | 1035 | active |
| juanjuandog/FinSight-AI FinSight AI is an open-source equity research workspace for A-share companies that turns market data, filings, and financial metrics into s… | 59 | 1034 | active |
| inclusionAI/UI-Venus UI-Venus is a family of open-source multimodal GUI agent models (9B/27B) that perform UI element grounding and task navigation from screens… | 63 | 1032 | active |
| OpenBMB/RepoAgent RepoAgent is an LLM-powered framework that automatically generates repository-level code documentation by detecting changes in Git reposito… | 24 | 1031 | active |
| minimaxir/simpleaichat A Python library providing a minimal, low-complexity interface for building applications on top of chat LLM APIs like ChatGPT and GPT-4. It… | 20 | 3500 | maintenance |
| walter-grace/mac-code A free, local coding agent for Apple Silicon Macs that runs large quantized LLMs (e.g., Qwen 35B) via llama.cpp, using techniques like flas… | 49 | 1026 | active |
| am-will/codex-skills A collection of Codex/agent skills written in Shell covering planning, documentation access, prompting, frontend design guidance, Codex too… | 57 | 1023 | active |
| AlexWan/OsEngine OsEngine is an open-source algorithmic trading platform written in C# that bundles a robot-creation layer, historical data downloader (OsDa… | 85 | 1022 | active |
| microsoft/skills-for-fabric A collection of reusable AI assistant skills and MCP systems from Microsoft for working with Microsoft Fabric workloads, APIs, and Power BI… | 82 | 1022 | active |
| SafeAI-Lab-X/ClawKeeper ClawKeeper is a host-agnostic safety middleware layer that sits between AI agents and their tools, blocking risky tool calls, redacting sen… | 59 | 1022 | active |