Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
claude-tap
AI repositoriesIntercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
git clone https://github.com/liaohch3/claude-tap.git -
harness
Agents & frameworksRun fleets of parallel coding agents with governance — Rust control plane for Claude Code & Codex: orchestration, policy, cross-agent review, observability.
git clone https://github.com/majiayu000/harness.git -
awesome-auditable-ai
Agents & frameworksAuditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attribution, and decision records.
git clone https://github.com/yzhao062/awesome-auditable-ai.git -
1flowbase
MCP serversBuild for agents — from the AI Gateway to the entire application stack.
git clone https://github.com/taichuy/1flowbase.git -
litefuse
Agents & frameworksLitefuse - Agent Observability and Evaluation Platform
git clone https://github.com/litefuse/litefuse.git -
sandbase-harness
MCP serversLocal-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
git clone https://github.com/sandbaseai/sandbase-harness.git -
Penelopa.ai
Tools & appsContinuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.
git clone https://github.com/chigwell/Penelopa.ai.git -
langwatch
PromptsOpen-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
git clone https://github.com/langwatch/langwatch.git -
prodagent
Agents & frameworksA minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核,理解 LangGraph/ADK 底层的工作原理
git clone https://github.com/limenagent/prodagent.git -
pi-harness
Agents & frameworksThe operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力,并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。
git clone https://github.com/wangmiaozero/pi-harness.git -
tma1
Agents & frameworksLocal-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.
git clone https://github.com/tma1-ai/tma1.git -
vnx-orchestration
Agents & frameworksGovernance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality gates, and full provenance.
git clone https://github.com/Vinix24/vnx-orchestration.git -
hello-agent-system
Docs & tutorials👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营
git clone https://github.com/heaven999b/hello-agent-system.git -
langfuse
Prompts🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
git clone https://github.com/langfuse/langfuse.git -
sugar
Agents & frameworksMission control for your agent fleet. One local-first board for Claude Code, Codex, Goose, Cursor and any MCP harness: durable tasks, live activity, cost attribution and audit exports.
git clone https://github.com/roboticforce/sugar.git -
Agent-Blackbox
Tools & appsLocal-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
git clone https://github.com/TaewoooPark/Agent-Blackbox.git -
coding.sh
MCP serversOpen-source, local-first observability and evals for AI agents: see what Claude Code, Codex, Cursor and others did and what it cost.
git clone https://github.com/jackulau/coding.sh.git -
AgentWatch
MCP serversMulti-agent observability: cascade failure detection, heartbeats, and forensic replay
@nicofains1/agentwatch@0.3.1 -
willdeep-cli
Agents & frameworks自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.
git clone https://github.com/niuwoai/willdeep-cli.git -
Rius
MCP serversQuery your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.
-
Browse Bridge
MCP serversLet AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.
-
Telesherpa Ontology Platform
MCP serversOntology platform for field service: AI agents observe, connect and act on business objects.
-
kyde score
MCP serversAgent observability via OpenTelemetry: drift, loop and hijack alerts, e.g. after a prompt injection.
-
crewplane
Agents & frameworksRun reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.
git clone https://github.com/crewplaneai/crewplane.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.