Top 100 Agent Runtime Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | herdr | 35,122 | 2,571 | Rust | 229 | the runtime your coding agents live on | 2026-09-03 |
| 2 | guizang-ppt-skill | 25,575 | 1,806 | HTML | 24 | AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime. | 2026-08-07 |
| 3 | OpenSandbox | 14,951 | 1,350 | Go | 93 | Secure, Fast, and Extensible Sandbox runtime for AI agents. | 2026-09-04 |
| 4 | holaOS | 11,137 | 721 | TypeScript | 3 | Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Clau... | 2026-08-21 |
| 5 | electric | 10,352 | 372 | TypeScript | 169 | The agent platform built on sync. | 2026-09-02 |
| 6 | deeplake | 9,230 | 723 | C++ | 52 | Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. | 2026-05-21 |
| 7 | OpenShell | 8,500 | 1,254 | Rust | 399 | OpenShell is the safe, private runtime for autonomous AI agents. | 2026-09-04 |
| 8 | open-multi-agent | 6,871 | 2,433 | TypeScript | 10 | TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepS... | 2026-09-03 |
| 9 | Kun | 6,275 | 595 | TypeScript | 13 | Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI. | 2026-09-04 |
| 10 | mission-control | 6,162 | 69 | TypeScript | 11 | Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes. | 2026-09-02 |
| 11 | ouroboros | 5,768 | 581 | Python | 54 | Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, ... | 2026-09-03 |
| 12 | trueforge | 5,185 | 366 | TypeScript | 47 | The open-source agent harness - the runtime layer that turns an LLM into a working agent. | 2026-09-03 |
| 13 | archestra | 4,243 | 1,188 | TypeScript | 24 | Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator | 2026-09-04 |
| 14 | cascadeflow | 3,968 | 908 | Python | 3 | Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop. | 2026-08-27 |
| 15 | atmosphere | 3,808 | 761 | Java | 2 | Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket... | 2026-09-03 |
| 16 | agent-sandbox | 3,735 | 481 | Go | 123 | agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL). | 2026-09-03 |
| 17 | agentcore-samples | 3,332 | 1,318 | Python | 240 | Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment. | 2026-09-03 |
| 18 | docker-agent | 3,304 | 450 | Go | 21 | AI Agent Builder and Runtime by Docker Engineering | 2026-09-03 |
| 19 | china-dictatorship | 3,180 | 292 | HTML | 837 | 反中共政治宣传库。Anti Chinese government propaganda. 住在中国真名用户的网友请别给星星，不然你要被警察请喝茶。常见问答集，新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件邓家贵低端人口西藏骚乱。Friends who live in China and have real name on ac... | 2026-02-05 |
| 20 | HotswapAgent | 2,613 | 520 | Java | 105 | Java unlimited redefinition of classes at runtime. | 2026-08-26 |
| 21 | shepherd | 2,395 | 206 | Python | 8 | A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write f... | 2026-08-09 |
| 22 | qwen-audio-agent | 2,331 | 201 | JavaScript | 9 | A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents | 2026-09-04 |
| 23 | harmonist | 2,258 | 206 | Python | 1 | Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies. | 2026-06-09 |
| 24 | .github | 1,995 | 152 | - | 0 | 这里是GitHub的草场，也是戈戈圈爱好者的交流地，主要讨论动漫、游戏、科技、人文、生活等所有话题，欢迎各位小伙伴们在此讨论趣事。This is GitHub grassland, and the community place for Gege circle lovers, mainly discusses anime, games, technology, lifing and other t... | 2025-10-04 |
| 25 | ax | 1,986 | 118 | Go | 34 | An open source distributed agent runtime | 2026-09-02 |
| 26 | BitFun | 1,985 | 218 | Rust | 100 | BitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond softwar... | 2026-09-04 |
| 27 | css | 1,947 | 44 | TypeScript | 1 | The markup-driven CSS language and framework — readable by humans, reliable for agents. | 2026-08-01 |
| 28 | ClawManager | 1,900 | 154 | Go | 12 | A Kubernetes-native control plane for AI agent instance management, with governed AI access, runtime orchestration, and reusable resources across multiple agent runtimes. | 2026-09-03 |
| 29 | failproofai | 1,843 | 436 | MDX | 20 | Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous f... | 2026-09-03 |
| 30 | bub | 1,597 | 156 | Python | 1 | Bub it. Build it. A hook-first runtime for agents that live alongside people. | 2026-09-01 |
| 31 | hermes-browser-extension | 1,492 | 139 | JavaScript | 5 | Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime. | 2026-08-27 |
| 32 | atmos | 1,369 | 173 | Go | 119 | Atmos is the open-source runtime for infrastructure — it builds, authenticates, and ships Terraform, OpenTofu, Packer, Ansible, Kubernetes, Helm, and containers the same way on your laptop, in CI, and... | 2026-09-04 |
| 33 | poco-claw | 1,353 | 126 | Python | 0 | A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, a sandboxed runtime and channel-based team collaboration. Under the hood, it is powered by ... | 2026-08-06 |
| 34 | boop-agent | 1,351 | 301 | TypeScript | 7 | iMessage personal agent: choose Claude Agent SDK (Claude Code) or Codex app-server runtime (Codex/ChatGPT), with memory, sub-agents, automations, integrations. | 2026-07-13 |
| 35 | overstory | 1,328 | 209 | TypeScript | 16 | Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more | 2026-05-28 |
| 36 | commonly | 1,325 | 185 | TypeScript | 117 | Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees. | 2026-09-04 |
| 37 | exo | 1,304 | 96 | Rust | 29 | Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks. | 2026-09-04 |
| 38 | sre | 1,289 | 202 | TypeScript | 7 | The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across... | 2026-04-03 |
| 39 | oh-my-agent | 1,264 | 146 | TypeScript | 1 | The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes. | 2026-09-03 |
| 40 | PhoneClaw | 1,232 | 167 | Swift | 2 | PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference. | 2026-08-06 |
| 41 | Hexabot | 1,207 | 240 | TypeScript | 11 | Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime. | 2026-08-24 |
| 42 | ai-agent-skills | 1,137 | 131 | JavaScript | 0 | Universal skill installer and package manager for AI coding agents. One command, 12+ runtimes. npx ai-agent-skills | 2026-08-17 |
| 43 | OpenRath | 1,133 | 59 | Python | 1 | An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows. | 2026-07-31 |
| 44 | AxisAgentic | 1,111 | 142 | Python | 0 | AxisAgentic: An Extensible Runtime and Trajectory-Collection Framework for Long-Horizon Agents. | 2026-07-24 |
| 45 | archive | 1,106 | 99 | Python | 4 | Skill Compose is an open-source agent builder and runtime platform for skill-powered agents. No workflow graphs. No CLI. | 2026-03-04 |
| 46 | HiveMind | 1,095 | 132 | Python | 2 | A Python-first runtime layer for multi-agent systems, with persistent run state, streaming execution events, and a pluggable orchestration interface. | 2026-09-04 |
| 47 | compose-for-agents | 1,028 | 467 | TypeScript | 10 | Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes. | 2026-09-02 |
| 48 | tensorlake | 996 | 140 | Python | 43 | Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications | 2026-09-04 |
| 49 | homerail | 929 | 204 | TypeScript | 24 | Voice-first local agent orchestration runtime for auditable DAG workflows. | 2026-09-01 |
| 50 | pi-gui | 920 | 145 | TypeScript | 26 | Electron GUI app for the pi coding agent runtime | 2026-07-28 |
| 51 | xpander.ai | 869 | 126 | Jupyter Notebook | 1 | xpander.ai is the runtime and control plane to build, run, and ship reliable AI agents fast and anywhere | 2025-11-11 |
| 52 | agentscope-runtime | 862 | 169 | Python | 55 | A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility. | 2026-06-04 |
| 53 | golf | 839 | 70 | Python | 2 | Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents | 2026-09-01 |
| 54 | ClawProBench | 823 | 54 | Rust | 1 | ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability. | 2026-08-25 |
| 55 | agentcookie | 814 | 66 | Go | 0 | Your agent runs on a Mac that isn't your daily driver. agentcookie keeps its sessions in sync with the Mac you actually browse on, continuously, encrypted over Tailscale, so OpenClaw, Hermes, or any o... | 2026-08-24 |
| 56 | atomic | 758 | 102 | TypeScript | 30 | The verifiable coding agent runtime. Define your coding agent's process in natural language with stages, checks, and approval gates instead of hoping it follows your instructions. | 2026-09-04 |
| 57 | bedrock-agentcore-sdk-python | 755 | 147 | Python | 78 | Python SDK for transforming any AI agent into a production-ready application. Framework-agnostic primitives for runtime, memory, authentication, and tools with AWS-managed infrastructure. | 2026-09-03 |
| 58 | dataagent | 752 | 99 | TypeScript | 4 | DataFoundry is an open-source AI workbench for data analysis, unifying data sources, knowledge, tools, and agent runtime into a governed workspace for interactive analytics. | 2026-09-03 |
| 59 | ima2-gen | 738 | 121 | TypeScript | 2 | Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers. | 2026-09-03 |
| 60 | tiri-agent | 727 | 125 | TypeScript | 0 | Tiri local agent backend and web shell built on agent-runtime. | 2026-07-02 |
| 61 | DongTai-agent-java | 697 | 203 | Java | 11 | Java Agent is a Java application probe of DongTai IAST, which collects method invocation data during runtime of Java application by dynamic hooks. | 2023-12-25 |
| 62 | wanman | 682 | 106 | TypeScript | 12 | wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent work... | 2026-06-14 |
| 63 | arcjet-js | 682 | 32 | TypeScript | 3 | Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code. | 2026-09-03 |
| 64 | evotown | 665 | 64 | Python | 31 | a middle platform for enterprise Agent runtime governance and capability assets — connect OpenClaw, Hermes, SkillLite, and custom runtimes in one place; accumulate Skills and enterprise knowledge; pro... | 2026-08-24 |
| 65 | swarmclaw | 660 | 137 | TypeScript | 8 | Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, ... | 2026-06-30 |
| 66 | youtube-skills | 654 | 62 | - | 0 | YouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, Hermes Agent, and other agent runtimes. | 2026-09-01 |
| 67 | sandbase-harness | 642 | 63 | TypeScript | 3 | Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console. | 2026-08-31 |
| 68 | harness-engineering-guide | 635 | 78 | TypeScript | 13 | 🔧 The open guide to Harness Engineering — concepts, tutorials, papers, tools, and resources for building and managing AI agent runtimes. | 2026-04-19 |
| 69 | activegraph | 629 | 57 | Python | 11 | Event-sourced graph runtime for durable and stateful agents | 2026-08-30 |
| 70 | agentos | 620 | 92 | TypeScript | 0 | TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers. | 2026-08-07 |
| 71 | ai00_server | 619 | 73 | Rust | 16 | The all-in-one RWKV runtime box with embed, RAG, AI agents, and more. | 2026-06-09 |
| 72 | anolisa | 618 | 108 | Rust | 83 | ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost. | 2026-09-04 |
| 73 | mda | 616 | 32 | TypeScript | 1 | MDA Open Spec — a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md, MCP-SERVER.md, and CLAUDE.md. JSON Schema validated, with typed dependency grap... | 2026-05-26 |
| 74 | ironcurtain | 600 | 79 | TypeScript | 3 | A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev) | 2026-09-04 |
| 75 | aislop | 593 | 29 | TypeScript | 6 | Catch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks, and more. 50+ deterministic rules across 10 language targe... | 2026-08-31 |
| 76 | fullstack-solution-template-for-agentcore | 584 | 184 | Python | 9 | Flexible Fullstack solution template for production-ready deployments of any use case on Amazon Bedrock AgentCore. | 2026-09-03 |
| 77 | Swarm | 574 | 43 | Swift | 0 | Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in one Swift-native runtime | 2026-08-29 |
| 78 | claw-orchestrator | 562 | 91 | TypeScript | 0 | Run Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-agent councils, an OpenAI-compatible endpoint, an MCP server, and an ACP agent any editor can... | 2026-09-04 |
| 79 | Adrian | 556 | 91 | Python | 3 | Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts. | 2026-08-20 |
| 80 | agentdock | 555 | 81 | Go | 4 | Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration. | 2026-09-04 |
| 81 | mnemon | 552 | 68 | Go | 3 | LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime. | 2026-09-03 |
| 82 | hol-guard | 538 | 29 | Python | 5 | Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime. | 2026-09-04 |
| 83 | clawless | 532 | 93 | TypeScript | 4 | ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers | 2026-07-08 |
| 84 | deer-workflow | 527 | 55 | TypeScript | 3 | An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes. | 2026-08-09 |
| 85 | LockKnife | 526 | 117 | Python | 1 | LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration ... | 2026-06-14 |
| 86 | bug-hunter | 502 | 60 | JavaScript | 0 | Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities... | 2026-08-17 |
| 87 | sandboxed.sh | 494 | 51 | Rust | 15 | Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets. | 2026-09-03 |
| 88 | openclaw.net | 490 | 99 | C# | 0 | Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly) | 2026-09-02 |
| 89 | agentguard | 458 | 67 | TypeScript | 5 | Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry. | 2026-09-02 |
| 90 | live-swe-agent | 455 | 45 | - | 7 | Live-SWE-agent: live, runtime self-evolving software engineering agent | 2026-01-19 |
| 91 | xcrawl-skills | 447 | 43 | - | 0 | Reusable Xcrawl skill definitions for multi-agent runtimes, focused on API-first web data workflows. | 2026-03-20 |
| 92 | Linghun | 435 | 22 | TypeScript | 0 | AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification. | 2026-08-19 |
| 93 | station | 429 | 41 | Go | 7 | Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control. | 2026-01-27 |
| 94 | ai4j | 428 | 55 | Java | 1 | Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...), Tool Calling, MCP, RAG, Agent Runtime, and a built-in Coding Agent CLI/TUI/ACP. | 2026-09-03 |
| 95 | pabar_agent_runtime | 423 | 0 | Python | 0 | agent runtime | 2026-07-28 |
| 96 | opencowork | 418 | 2 | TypeScript | 0 | Open-source, local-first desktop Agent Runtime for turning business goals into executable, reusable, and auditable workflows. | 2026-06-05 |
| 97 | reticle | 417 | 107 | TypeScript | 70 | AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications. | 2026-09-02 |
| 98 | clawmetry | 404 | 64 | Python | 115 | See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, OpenHands, Aider, Goose, OpenClaw, NVIDIA N... | 2026-09-04 |
| 99 | kode-agent-sdk | 397 | 73 | TypeScript | 5 | Open runtime for building Claude Code & Manus like Agent Product | 2026-07-10 |
| 100 | termio | 396 | 32 | Swift | 22 | A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, tmux alternative, Remote Linux VPS supported | 2026-09-03 |