InnerVault

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

  1. claude-tap

    AI repositories

    Intercept 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.

    Stale GitHub, liaohch3 3,332 ★MITUpdated 6 days ago

    git clone https://github.com/liaohch3/claude-tap.git
  2. harness

    Agents & frameworks

    Run fleets of parallel coding agents with governance — Rust control plane for Claude Code & Codex: orchestration, policy, cross-agent review, observability.

    Indexed GitHub, majiayu000 92 ★MITUpdated yesterday

    git clone https://github.com/majiayu000/harness.git
  3. awesome-auditable-ai

    Agents & frameworks

    Auditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attribution, and decision records.

    Stale GitHub, yzhao062 154 ★CC0-1.0Updated 28 days ago

    git clone https://github.com/yzhao062/awesome-auditable-ai.git
  4. 1flowbase

    MCP servers

    Build for agents — from the AI Gateway to the entire application stack.

    Stale GitHub, taichuy 287 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/taichuy/1flowbase.git
  5. litefuse

    Agents & frameworks

    Litefuse - Agent Observability and Evaluation Platform

    Indexed GitHub, litefuse 113 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/litefuse/litefuse.git
  6. sandbase-harness

    MCP servers

    Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

    Stale GitHub, sandbaseai 639 ★Apache-2.0Updated 15 days ago

    git clone https://github.com/sandbaseai/sandbase-harness.git
  7. Penelopa.ai

    Tools & apps

    Continuous 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.

    Stale GitHub, chigwell 139 ★AGPL-3.0Updated 43 days ago

    git clone https://github.com/chigwell/Penelopa.ai.git
  8. langwatch

    Prompts

    Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.

    Indexed GitHub, langwatch 5,038 ★Apache-2.0Updated today

    git clone https://github.com/langwatch/langwatch.git
  9. prodagent

    Agents & frameworks

    A 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

    Stale GitHub, limenagent 122 ★MITUpdated 26 days ago

    git clone https://github.com/limenagent/prodagent.git
  10. pi-harness

    Agents & frameworks

    The 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。

    Indexed GitHub, wangmiaozero 390 ★AGPL-3.0Updated today

    git clone https://github.com/wangmiaozero/pi-harness.git
  11. tma1

    Agents & frameworks

    Local-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.

    Stale GitHub, tma1-ai 122 ★Apache-2.0Updated 17 days ago

    git clone https://github.com/tma1-ai/tma1.git
  12. vnx-orchestration

    Agents & frameworks

    Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality gates, and full provenance.

    Indexed GitHub, Vinix24 63 ★MITUpdated yesterday

    git clone https://github.com/Vinix24/vnx-orchestration.git
  13. 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

    Stale GitHub, heaven999b 187 ★MITUpdated 49 days ago

    git clone https://github.com/heaven999b/hello-agent-system.git
  14. 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.

    Indexed GitHub, langfuse 37.5k ★Custom licence (see repository)Updated today

    git clone https://github.com/langfuse/langfuse.git
  15. sugar

    Agents & frameworks

    Mission 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.

    Stale GitHub, roboticforce 100 ★Custom licence (see repository)Updated 6 days ago

    git clone https://github.com/roboticforce/sugar.git
  16. Agent-Blackbox

    Tools & apps

    Local-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.

    Stale GitHub, TaewoooPark 83 ★MITUpdated 14 days ago

    git clone https://github.com/TaewoooPark/Agent-Blackbox.git
  17. coding.sh

    MCP servers

    Open-source, local-first observability and evals for AI agents: see what Claude Code, Codex, Cursor and others did and what it cost.

    Indexed GitHub, jackulau 30 ★MITUpdated today

    git clone https://github.com/jackulau/coding.sh.git
  18. AgentWatch

    MCP servers

    Multi-agent observability: cascade failure detection, heartbeats, and forensic replay

    Stale Official MCP Registry, io.github.nicofains1 Updated 8 months ago 1 note

    @nicofains1/agentwatch@0.3.1
  19. 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.

    Indexed GitHub, niuwoai 201 ★Custom licence (see repository)Updated today

    git clone https://github.com/niuwoai/willdeep-cli.git
  20. Rius

    MCP servers

    Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.

    Stale Official MCP Registry, ai.glassflow Updated 3 days ago 1 note

  21. Browse Bridge

    MCP servers

    Let AI agents observe and control Chrome tabs you explicitly share via Browse Bridge.

    Stale Official MCP Registry, com.browsebridge Updated 20 days ago 1 note

  22. Ontology platform for field service: AI agents observe, connect and act on business objects.

    Stale Official MCP Registry, com.telesherpa Updated 7 days ago 1 note

  23. kyde score

    MCP servers

    Agent observability via OpenTelemetry: drift, loop and hijack alerts, e.g. after a prompt injection.

    Stale Official MCP Registry, com.kyde Updated 2 days ago 1 note

  24. crewplane

    Agents & frameworks

    Run 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.

    Indexed GitHub, crewplaneai 54 ★Apache-2.0Updated today

    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.