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-fable-5-claude-code

    Datasets & benchmarks

    Hugging Face dataset by armand0e

    Indexed Hugging Face Hub, armand0e 416 ♥mitUpdated 2 months ago

    armand0e/claude-fable-5-claude-code
  2. AgentTrove

    Datasets & benchmarks

    Hugging Face dataset by open-thoughts

    Stale Hugging Face Hub, open-thoughts 202 ♥apache-2.0Updated 6 months ago

    open-thoughts/AgentTrove
  3. pi-mono

    Datasets & benchmarks

    Hugging Face dataset by badlogicgames

    Stale Hugging Face Hub, badlogicgames 219 ♥otherUpdated 7 months ago

    badlogicgames/pi-mono
  4. agent-trace-auditor

    MCP servers

    Cloudflare Workers MCP server: agent-trace-auditor

    Stale Official MCP Registry, io.github.lazymac2x Updated 6 months ago 1 note

  5. Step-by-step observability for MCP agent workflows

    Stale Official MCP Registry, io.github.dbsectrainer Updated 12 days ago 2 notes

    mcp-agent-trace-inspector@1.0.1
  6. failproofai

    AI repositories

    Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.

    Stale GitHub, FailproofAI 6,226 ★Custom licence (see repository)Updated 22 days ago

    git clone https://github.com/FailproofAI/failproofai.git
  7. Agent Trace Check

    MCP servers

    Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.

    Stale Official MCP Registry, app.openkrill Updated 31 days ago 1 note

  8. fable-5-premium

    Datasets & benchmarks

    Hugging Face dataset by saidutta69

    Stale Hugging Face Hub, saidutta69 136 ♥mitUpdated 2 months ago

    saidutta69/fable-5-premium
  9. console

    MCP servers

    Open-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.

    Indexed GitHub, Cognipeer 27 ★AGPL-3.0Updated 4 days ago

    git clone https://github.com/Cognipeer/console.git
  10. mas-lab

    Agents & frameworks

    Specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP, and A2A.

    Indexed GitHub, ioc-project 65 ★Apache-2.0Updated yesterday

    git clone https://github.com/ioc-project/mas-lab.git
  11. agent-apprenticeship

    Agents & frameworks

    The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

    Stale GitHub, ray-r-ren 1,616 ★MITUpdated 37 days ago

    git clone https://github.com/ray-r-ren/agent-apprenticeship.git
  12. SpanHound

    MCP servers

    Capture local agent traces and inspect failures, approvals, and run comparisons.

    Stale Official MCP Registry, io.github.abhishekash Updated 32 days ago 1 note

    spanhound@0.6.1
  13. CyberHuaTuo

    MCP servers

    Gold-first AI-agent traceback diagnosis, exact fixes, verification, and reusable prescriptions.

    Stale Official MCP Registry, io.github.JinNing6 Updated 4 months ago 1 note

    cyberhuatuo@0.2.5
  14. Agent tracing, cost tracking, anomaly detection for LLM agents

    Stale Official MCP Registry, io.github.mdfifty50-boop Updated 6 months ago 1 note

    agentic-observability-mcp@0.1.1
  15. tracelane-mcp

    MCP servers

    Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts

    Stale Official MCP Registry, io.github.tracelane Updated 38 days ago 2 notes

    @tracelanedev/mcp@0.4.0
  16. tracecrate

    Tools & apps

    Local-first AI agent trace workbench. Inspect Claude Code, Codex and OTLP logs, compare runs, and export privacy-conscious reports. No backend or API keys.

    Stale GitHub, FankChen 196 ★MITUpdated 25 days ago

    git clone https://github.com/FankChen/tracecrate.git
  17. agentguard47

    MCP servers

    Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.

    Stale Official MCP Registry, io.github.bmdhodl Updated 5 months ago 2 notes

    @agentguard47/mcp-server@0.2.2
  18. LightShip

    MCP servers

    Governed access to production AI-agent traces in an existing ClickHouse store.

    Stale Official MCP Registry, io.github.lightshipHQ Updated 2 months ago 1 note

  19. evr

    MCP servers

    Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.

    Stale Official MCP Registry, io.github.BrienBounded Updated 3 months ago 1 note

    evidence-readiness@0.1.2
  20. agentrace

    MCP servers

    Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer.

    Stale Official MCP Registry, io.github.ura-tools Updated 7 months ago 1 note

    @ura-dev/agentrace@1.0.0
  21. PyAI Voice AI

    MCP servers

    Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.

    Indexed Official MCP Registry, io.github.atomsai Updated today 2 notes

    @pyai/mcp@0.5.17
  22. 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

  23. EvalGate

    MCP servers

    Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.

    Stale Official MCP Registry, com.evalgate Updated 11 days ago 1 note

  24. DM-Code-Agent

    Agents & frameworks

    An inspectable coding agent. Trace changes, diagnose failed runs, and share test evidence. Local-first Python, no-key demo, standalone HTML reports.

    Indexed GitHub, hwfengcs 152 ★MITUpdated yesterday

    git clone https://github.com/hwfengcs/DM-Code-Agent.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.