🔓🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
// uncategorizedlobehub/⟨TypeScript⟩★ 82,931◷ NOASSERTION[ claude ]
Projects tagged #agent-harness
// agent-harness (25)
🔓
🔓Open-source AI agent workspace. Run any agent — Claude Code, Codex — across your tools (100+ integrations + MCP), apps, browser, and files, with shared memor…
// uncategorizedholaboss-ai/⟨TypeScript⟩★ 11,456◷ NOASSERTION[ claude ]
🔓an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, us…
// devtoolsHarnessMD/⟨TypeScript⟩★ 8,299◷ MIT[ claude ]
🔓Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.
// uncategorizedloopx-project/⟨Python⟩★ 6,136◷ Apache-2.0[ claude ]
🔓Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.
// uncategorizedhuangruiteng/⟨Python⟩★ 5,987◷ Apache-2.0[ claude ]
🔓Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashb…
// uncategorizedFailproofAI/⟨MDX⟩★ 5,146◷ NOASSERTION[ claude ]
🔓Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.
// devtoolsmvschwarz/⟨TypeScript⟩★ 4,722◷ Apache-2.0[ claude ]
🔓Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
// automationai-boost/⟨Python⟩★ 4,611◷ NOASSERTION[ claude ]
🔓AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider…
// automationzhnt/⟨Python⟩★ 1,660◷ Apache-2.0[ claude ]
🔓Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
// automationthClaws/⟨Rust⟩★ 1,227◷ Apache-2.0[ claude ]
🔓Open-source, multi-platform harness for AI agents — a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or Open…
// mcp-serversrisa-labs-inc/⟨Kotlin⟩★ 809◷ Apache-2.0[ claude ]
🔓🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-si…
// automationruvnet/⟨TypeScript⟩★ 688◷ MIT[ claude ]
🔓🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-si…
// mcp-serversruvnet/⟨TypeScript⟩★ 686◷ MIT[ claude ]
🔓Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
// mcp-serverssandbaseai/⟨TypeScript⟩★ 677◷ Apache-2.0[ claude ]
🔓从零写一个能活下来的 AI Agent：15 课可跑代码，机制从真实产品 Reina 移植 | Build a coding agent from scratch — how Claude Code / Codex / Cursor actually work under the hood. 15 runnabl…
// devtools7-e1even/⟨JavaScript⟩★ 285◷ MIT[ claude ]
🔓The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and C…
// ragJakeSelby/⟨Python⟩★ 22◷ MIT[ claude ]
🔓Find out which of your agent rules actually fire. An agentic coding harness for Claude Code and Codex: one checkout of rules, skills, subagents, slash comman…
// ragJakeSelby/⟨Python⟩★ 24◷ MIT[ claude ]
🔓Execution posture harness for Claude Code. Your coding agent stops one step early; Castra is the step.
// automationbeyondworks/⟨Python⟩★ 33◷ MIT[ claude ]
🔓Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec pas…
// devtoolsSihyeonJeon/⟨Python⟩★ 46◷ MIT[ claude ]
🔓Runtime for coding-agent harnesses. Run Claude Code, Codex, OpenCode, Pi, and Grok in one terminal; hop live between them; search or resume any local session.
// raghetpatel-11/⟨Rust⟩★ 31◷ MIT[ claude ]
🔓A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.
// pluginsSeoNaRu/⟨Python⟩★ 34◷ MIT[ claude ]
🔓Your AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP servers once; apply…
// mcp-serversucsandman/⟨JavaScript⟩★ 22◷ MIT[ claude ]
🔓Open & nano reimplementation of Sakana Fugu. A repo-native, multi-agent coding loop powered by 9+ LLMs (isolated via Claude Code) and an independent Codex re…
// devtoolsBicaMindLabs/⟨TypeScript⟩★ 28◷ Apache-2.0[ claude ]
🔓Specs both you and the AI understand. An agent team fitted to your repo. Guardrails that block, not advise. Two Claude Code skills - spec-builder + harness-b…
// devtoolsnguyenhx2/⟨HTML⟩★ 13◷ MIT[ claude ]
🔓Finish-First Autonomous Agent Loop for Claude Opus 4.7 – 2026 Edition
// automationMagma1321/⟨HTML⟩★ 145[ claude ]