Ross ROSS = Recommend OSS · open-source software intelligence for agents

Open-source agent-framework software

2398 open-source libraries, tools and applications tagged agent-framework, ranked by how closely agent-framework is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.

2398 products, primary matches first, then adoption-weighted; health v2 shown.

ProductHealth v2StarsMaturity
omnimind-ai/OmniBot
OpenOmniBot (OmniBot) is an on-device AI agent app for Android, built with a native Kotlin host and Flutter UI, that runs a full understand…
752010active
openclaw/clawsweeper
ClawSweeper is a conservative GitHub maintenance bot that reviews open issues and pull requests on a schedule, writes durable markdown repo…
762004active
GoogleCloudPlatform/scion
Scion is a multi-agent orchestration platform that runs 'deep agents' like Claude Code and Gemini CLI in isolated containers, each with its…
692003active
patterns-ai-core/langchainrb
Langchain.rb is a Ruby library for building LLM-powered applications, providing a unified interface to many LLM providers (OpenAI, Anthropi…
732001active
zouyuxuan122/Deepseek-Harness-EAC
Deepseek Harness EAC is a Windows (and macOS) desktop client that wraps the official DeepSeek agent harness CLI (@deepseek-ai/dsh) into a o…
802000active
GuDaStudio/codexmcp
CodexMCP is an MCP server that bridges Claude Code and OpenAI Codex CLI, letting the two AI coding agents collaborate with each other. It a…
422000active
tsingyuai/growth-lab
Growth Lab is an open-source, end-to-end AI growth system that runs product marketing and user-acquisition loops through natural-language c…
571991active
openakita/openakita
OpenAkita is an open-source multi-agent AI assistant framework in Python that orchestrates multiple cooperating agents with skills, plugins…
761990active
RedPlanetHQ/core
CORE is an open-source, self-hosted personal AI operating system that runs as an always-on assistant with persistent memory and integration…
771984active
glittercowboy/taches-cc-resources
A curated collection of custom Claude Code resources including 27 slash commands, 9 skills, and 3 auditor subagents for structured workflow…
471983active
mudler/LocalAGI
LocalAGI is a self-hostable, privacy-focused AI agent platform written in Go that lets users create no-code agents, automations, and chatbo…
851979active
anthropics/defending-code-reference-harness
A reference implementation from Anthropic for autonomous vulnerability discovery and remediation using Claude, including Claude Code skills…
547548maintenance
aipoch/medical-research-skills
A curated library of 550+ SKILL.md-compatible agent skills for medical and biomedical research, covering evidence insights, protocol design…
701971active
showlab/computer_use_ootb
An out-of-the-box desktop GUI agent that lets vision-language models like Claude 3.5 Computer Use, ShowUI, and UI-TARS control Windows and …
291965active
huang-sir1/radiology-skills
An open-source collection of 27 Claude/Codex 'skills' (modular rule files) for medical imaging research, covering radiomics, deep learning,…
671962active
Agent Shell
agent-shell is an Emacs Lisp package that provides a native Emacs buffer interface for interacting with LLM coding agents (Claude Code, Ope…
631962active
ai4s-research/open-science
Open Science Desktop is a local-first, model-agnostic AI research workbench for macOS, Windows, and Linux, built with Tauri, MCP, and agent…
811961active
alvinunreal/tmuxai
TmuxAI is an open-source, AI-powered terminal assistant that runs inside tmux sessions, observing pane content and helping execute commands…
851952active
HKUDS/VideoAgent
VideoAgent is an all-in-one agentic framework for video understanding, editing, and remaking, built on multi-agent orchestration with over …
571951active
Darkatse/TauriTavern
TauriTavern is a native rewrite of SillyTavern built with Tauri v2 and a Rust backend, providing the classic LLM chat/roleplay frontend as …
861948active
microsoft/Magma
Magma is Microsoft Research's foundation model for multimodal AI agents, released as an 8B vision-language model that understands images an…
501948active
OpenBMB/StaffDeck
StaffDeck is an open-source enterprise platform for building and managing AI-powered digital employees that codify professional experience,…
781944active
databricks-solutions/ai-dev-kit
A Databricks Field Engineering toolkit that provides skills, an MCP server, and a Builder App for AI coding agents working with the Databri…
751942active
getnao/nao
nao is an open-source framework for building and deploying analytics agents that answer natural-language questions about data. It combines …
791936active
wuyoscar/Internal-Safety-Collapse
ISC-Bench/TVD is a research framework for studying 'Internal Safety Collapse' in frontier LLMs, where agents placed in adversarial codespac…
601935active
severity1/claude-code-prompt-improver
A Claude Code hook plugin that intelligently improves prompts at submit time, tool use, and subagent start, injecting contextual nudges so …
681932active
SMNETSTUDIO/WeChat-AI
A self-hosted WeChat roleplay chatbot service written in TypeScript that connects directly to Tencent iLink, stores data in remote Redis, a…
651931active
YoMo
YoMo is an open-source serverless LLM function calling framework for building fast, geo-distributed AI agents, written in Rust with a QUIC-…
971929active
CoderGamester/mcp-unity
A Unity Editor plugin implementing the Model Context Protocol (MCP) that lets AI coding assistants like Cursor, Claude Code, Codex, and Win…
821923active
IPADS-SAI/MobiAgent
MobiAgent is a systematic framework for building customizable GUI agents that operate mobile phones, comprising the MobiMind agent model fa…
541920active
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…
521919active
yologdev/yoyo-evolve
yoyo is an open-source terminal coding agent written in Rust that autonomously evolves its own source code — reading its code, planning imp…
831917active
Jesseovo/last30days-skill-cn
An AI Agent skill (for Claude Code / OpenClaw) that automatically searches content from the last 30 days across 8 major Chinese internet pl…
591916active
Dicklesworthstone/pi_agent_rust
pi_agent_rust is a native, single-binary AI coding agent CLI written in Rust with zero unsafe code, ported from Mario Zechner's Pi Agent. I…
831914active
hanshuaikang/nezha
Nezha is a lightweight cross-platform desktop IDE designed for the AI coding era, letting you run and monitor multiple Claude Code and Code…
791907active
melih-unsal/DemoGPT
DemoGPT is a Python framework and autonomous agent that generates LangChain-based LLM agent applications from natural-language prompts, bun…
511906active
ShenSeanChen/waku-agent
Waku Agent is a local-first AI agent harness in Python that exposes the full agent stack — harness, loop, memory, and eval/LLM-Ops — as sma…
791903active
BidingCC/BuildingAI
BuildingAI is an open-source, enterprise-grade platform for visually assembling AI applications without code, described as the 'WordPress o…
801900active
Th0rgal/open-ralph-wiggum
A CLI tool that runs AI coding agents (Claude Code, Codex, Copilot CLI, Cursor Agent, Qwen Code, OpenCode) in an autonomous iterative 'Ralp…
661895active
TencentEdgeOne/edgeone-makers-tools
Official AI agent skills package for Tencent EdgeOne Makers, installable into AI coding agents like Claude Code, Cursor, Codex, and CodeBud…
581894active
zakirkun/guardian-cli
Guardian is a Python CLI tool that automates penetration testing workflows using LLM providers (OpenAI, Claude, Gemini, Ollama, and others)…
631889active
SqueezeAILab/LLMCompiler
LLMCompiler is a Python framework from an ICML 2024 paper that orchestrates parallel function calling with LLMs. It uses a planner, task fe…
271889active
nolanx-ai/nolanx.ai
NolanX is an open-source multi-modal agent platform for AI filmmaking that orchestrates text, image, audio, and video models into long-runn…
491877active
Jido
Jido is an autonomous agent framework for Elixir that runs agents as supervised BEAM processes with fault tolerance, signal-based coordinat…
811875active
zhu1090093659/deepseek-pp
DeepSeek++ is an open-source browser extension for Chrome, Edge, and Firefox that turns the DeepSeek web app into an AI agent workspace. It…
101870active
stephengpope/thepopebot
A self-hosted autonomous AI agent platform that combines chat (Telegram and web), coding agents (Claude Code, Codex, Gemini, etc.), and liv…
641862active
HITsz-TMG/VideoClaw
VideoClaw is an AI director system that turns a one-line idea or story synopsis into a fully automated video production pipeline, covering …
641861active
questflowai/investorskills
An open-source library of portable, plain-text 'investor skill' packages (SKILL.md files plus investment schemas) that encode the judgment …
551861active
SuperDesign
SuperDesign is an open-source AI design agent that lives inside your IDE (VS Code, Cursor, Windsurf, Claude Code) and generates UI mockups,…
567025maintenance
nimbalyst/nimbalyst
Nimbalyst is an open-source (MIT) Electron desktop app that serves as a visual workspace for running AI coding agents like Claude Code, Cod…
831850active
HKUDS/OpenOPC
OpenOPC is a Python framework for building a personal AI-native company that recruits role-specific AI employees, assigns and hands off tas…
561848active
shiwenwen/hope-agent
Hope Agent is a local-first, cross-device desktop AI assistant built with Rust and Tauri that features long-term memory, autonomous goal pu…
781843active
trpc-group/trpc-agent-go
tRPC-Agent-Go is a Go-native framework for building production LLM agent systems, offering agents, graph workflows (LangGraph-equivalent), …
791836active
he-yufeng/CoreCoder
CoreCoder is a minimal AI coding agent written in roughly 1,000 lines of Python, inspired by Claude Code and designed to work with any LLM.…
821833active
a5c-ai/babysitter
Babysitter is an npm-distributed CLI and runtime that enforces deterministic, step-by-step process control on AI coding agents across 12 su…
721831active
a9gent/mindfs
MindFS is a self-hosted web gateway that lets you access personal AI coding agents (Claude Code, Codex, Gemini CLI, Cursor, and many others…
801830active
Stitch
A collection of Agent Skills and plugins for Google Stitch, Google's AI design tool, following the Agent Skills open standard. It integrate…
741830active
OpenAgentPlatform/Dive
Dive is an open-source MCP host desktop application that connects to any LLM supporting function calling, including ChatGPT, Anthropic, Oll…
751828active
ReScienceLab/opc-skills
A collection of open-source Agent Skills (folders of instructions, scripts, and resources) designed for solopreneurs, indie hackers, and on…
691825active
phodal/routa
Routa is a workspace-first multi-agent coordination platform for AI-assisted software delivery, exposing goals, tasks, sessions, traces, an…
721822active
Mellea
Mellea is a Python library for writing generative programs, where LLM calls are first-class operations with type-annotated outputs, verifia…
841821active
Core-Mate/OpenGUI
OpenGUI is an Android GUI agent framework that lets AI agents see, understand, and operate real mobile app interfaces on physical Android d…
801815active
Besty0728/Unity-Skills
UnitySkills is a REST API-based automation engine that lets AI coding assistants (Claude Code, Cursor, Codex, Gemini CLI, Antigravity, Open…
781815active
zi-yue-1129/DATAGEN
DATAGEN is an AI-powered multi-agent research and data analysis platform built with LangChain, LangGraph, and OpenAI GPT models. It automat…
681810active
Jedward23/Tmux-Orchestrator
A Python-based orchestration tool that runs AI coding agents (like Claude) inside tmux sessions, enabling hierarchical multi-agent coordina…
301807active
undertheseanlp/underthesea
Underthesea is an open-source Python toolkit for Vietnamese natural language processing that has evolved into an agentic AI toolkit with mu…
911806active
granawkins/rawdog
Rawdog is a CLI assistant that responds to natural-language prompts by generating and auto-executing Python scripts. It uses a recursive se…
301803active
microsoft/CyberBattleSim
CyberBattleSim is a Python-based experimentation and research platform from Microsoft that simulates abstract enterprise network environmen…
771800active
LM Studio SDK
lmstudio-js is the official TypeScript/JavaScript client SDK for LM Studio, enabling use of locally running LLMs for chat, completions, emb…
731799active
onestardao/WFGY
WFGY is an open-source ecosystem of protocols and tools for debugging and improving AI reasoning, RAG pipelines, and agent workflows, curre…
771794active
OS-Copilot/OS-Copilot
OS-Copilot is an open-source Python library for building generalist AI agents that interface with operating system elements like the web, t…
171794active
vercel-labs/coding-agent-template
A deployable Next.js web application template for building multi-agent AI coding platforms that run coding agents like Claude Code, Codex C…
591792active
hitsz-ids/airda
airda (Air Data Agent) is a Python-based multi-agent system for data analysis that understands natural language data requirements and gener…
171792active
standardagents/dmux
dmux is a terminal-based multiplexer that manages multiple AI coding agents in parallel using tmux panes and isolated git worktrees. Each t…
781788active
anthropics/claude-agent-sdk-typescript
The Claude Agent SDK is a TypeScript/Node.js library for programmatically building AI agents powered by Claude Code's capabilities. It enab…
801785active
MCP Hub
MCP Hub is a Neovim plugin that acts as an MCP (Model Context Protocol) client, integrating MCP servers into the editing workflow. It provi…
471785active
OpenAdaptAI/OpenAdapt
OpenAdapt is a Python framework that compiles a demonstrated GUI workflow into an inspectable, deterministic, locally executable program fo…
941784active
Simple-Efficient/RL-Factory
RLFactory is a reinforcement learning post-training framework for training agentic LLM models, decoupling the environment from RL training …
311783active
google-deepmind/concordia
Concordia is a Python library for building generative agent-based social simulations, using a tabletop role-playing game pattern where a Ga…
831782active
FSoft-AI4Code/CodeWiki
CodeWiki is an open-source Python framework that uses LLM-powered multi-agent processing to generate holistic, structured documentation for…
581778active
ExtensityAI/symbolicai
SymbolicAI is a Python neuro-symbolic framework that blends classical programming with LLM capabilities through composable Symbol primitive…
931777active
AidanPark/openclaw-android
A tool that runs OpenClaw (an AI agent gateway) natively on Android via Termux using only the glibc dynamic linker, avoiding a full proot L…
831775active
kenn-io/roborev
roborev is a Go-based continuous code review tool for AI coding agents that reviews every commit in the background via git hooks and surfac…
791769active
AgentDock/AgentDock
AgentDock is an open-source, backend-first TypeScript framework for building AI agents with configurable determinism, plus a Next.js refere…
681766active
signerlabs/Klee
Klee is a native macOS AI chat application that runs large language models entirely on-device using Apple's MLX framework on Apple Silicon.…
501765active
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…
771763active
GoogleCloudPlatform/agent-starter-pack
A Python package from Google Cloud Platform that provides production-ready templates for building and deploying GenAI agents on Google Clou…
686569maintenance
mims-harvard/ToolUniverse
ToolUniverse is a Python SDK and MCP server that aggregates a large collection of scientific tools (APIs, databases, local ML and cheminfor…
841754active
run-llama/rags
A Streamlit web app that lets users build a RAG (retrieval-augmented generation) pipeline over their data using natural language instructio…
276551maintenance
HKUDS/Auto-Deep-Research
Auto-Deep-Research is an open-source, cost-efficient alternative to OpenAI's Deep Research, built on the AutoAgent framework. It runs as a …
381750active
sunny-glow/Auto-BenchMax
Auto-BenchMax is a Python pipeline that automatically synthesizes benchmark-targeted training data for LLMs, claiming to more than double a…
521745active
RazorConsole/RazorConsole
RazorConsole is a .NET framework for building rich, interactive terminal user interfaces (TUIs) using Razor component syntax on top of Spec…
831740active
Gitlawb/zero
Zero is a terminal-based AI coding agent written in Go that can inspect repositories, edit files, run commands, and manage durable local se…
801736active
juliye2025/evil-read-arxiv
A collection of Claude Code / OpenAI Codex skills plus a Next.js web app that automates research paper discovery, analysis, and note-taking…
581735active
elder-plinius/V3SP3R
V3SP3R (Vesper) is an Android application that turns a Flipper Zero into an AI-controlled hardware hacking tool, driven by natural language…
451735active
LLPhant/LLPhant
LLPhant is a comprehensive PHP generative AI framework inspired by LangChain and LlamaIndex, providing tools for working with LLMs, embeddi…
961722active
openkursar/hello-halo
Halo is an open-source desktop AI workstation that wraps frontier coding agents like Claude Code and Codex in a visual GUI, with a pluggabl…
811719active
NeoLabHQ/context-engineering-kit
A hand-crafted collection of Claude Code Skills and plugins implementing context engineering techniques to improve AI coding agent output q…
781719active
Lynpoint/CyberVerse
CyberVerse is an open-source, self-hosted framework for building real-time, voice-first AI agents with optional digital-human video (talkin…
611719active
Pentest AI
pentest-ai is an MIT-licensed local CLI and MCP server that turns Claude Code (or any LLM) into an offensive security assistant, pairing 50…
791717active

← prev page 11 / 24 next →