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. Hlido Agent Reviews

    MCP servers

    Independent AI-agent reviews: trust checks, evidence scorecards, incident registry, recommendations.

    Stale Official MCP Registry, eu.hlido Updated 5 months ago 1 note

  2. 让 Agent 的工作方式可组合、可审查、可持续改进,最终实现 Agent Self Evoling。 DeepSeek Harness Web plugin with composable task controls and isolated, human-reviewed self-evolution.

    Stale GitHub, GraySilver 200 ★MITUpdated 11 days ago

    git clone https://github.com/GraySilver/dsh-evolve-modes.git
  3. One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

    Indexed GitHub, yzhao062 262 ★Apache-2.0Updated today

    git clone https://github.com/yzhao062/anywhere-agents.git
  4. ProductIndex

    MCP servers

    Product research for AI agents: review-synthesized verdicts, specs, prices and seller quotes.

    Stale Official MCP Registry, ai.productindex Updated 28 days ago 1 note

  5. kandev

    Tools & apps

    AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

    Indexed GitHub, kdlbs 1,131 ★AGPL-3.0Updated today

    git clone https://github.com/kdlbs/kandev.git
  6. MentionAgent

    MCP servers

    Link building outreach from your agent: review drafts, send the batch, answer publisher replies.

    Stale Official MCP Registry, ai.mentionagent Updated 9 days ago 1 note

  7. Metis

    MCP servers

    Governed tacit memory for AI agents: reviewed expert know-how, given only where conditions match

    Stale Official MCP Registry, io.github.BrightbeamAI Updated 42 days ago 1 note

    metis-memory@0.1.6
  8. MoltJobs

    MCP servers

    Browse MoltJobs jobs, manage owned AI agents, review evals, and place authorized USDC bids.

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

  9. hilos workspace

    MCP servers

    Operate hilos project rooms, Docs, Tasks, messages, memory, and coding-agent review workflows.

    Stale Official MCP Registry, sh.hilos Updated 2 months ago 1 note

  10. Make Agent Fast

    MCP servers

    Create customer-service agents, review conversations and leads, and improve answers.

    Stale Official MCP Registry, io.github.abdurshd Updated 21 days ago 1 note

  11. Docsworth

    MCP servers

    Team-owned docs for coding agents: review SLAs, a citation gate, and PR-only writes.

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

    @docsworth/cli@0.3.2
  12. Chatley AI

    MCP servers

    Manage Chatley AI voice agents: review calls, transcripts and analytics, and edit agents safely.

    Stale Official MCP Registry, ai.chatley Updated 33 days ago 1 note

  13. Monologue

    MCP servers

    One private feed for you and your AI agents. Review reported actions with permission.

    Stale Official MCP Registry, io.github.willcheung Updated 41 days ago 1 note

  14. Agentosaurus

    MCP servers

    Claude Code policy gateway, prices, AI-agent reviews and Amsterdam sustainability data as MCP tools.

    Indexed Official MCP Registry, com.agentosaurus Updated today 1 note

  15. 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
  16. rigour

    MCP servers

    Lets coding agents review their change, find an existing helper, and recall the team's lessons.

    Stale Official MCP Registry, io.github.rigour-labs Updated 28 days ago 1 note

    @rigour-labs/mcp@7.0.14
  17. Ghosty

    MCP servers

    Your Ghosty account: talk to your AI agents, review chats and work your sales board. OAuth.

    Stale Official MCP Registry, studio.ghosty Updated 34 days ago 1 note

  18. A ready-to-fork Claude Code template for academic research — papers, data analysis (R, Stata, Python), slides and teaching — with multi-agent review, enforced quality gates and replication protocols. Codex and Antigravity can use it too.

    Stale GitHub, pedrohcgs 1,689 ★MITUpdated 9 days ago

    git clone https://github.com/pedrohcgs/claude-code-my-workflow.git
  19. connect

    MCP servers

    Find tools ranked by measured behaviour, read agent reviews, and talk to other people's agents.

    Stale Official MCP Registry, io.github.husk-security Updated 46 days ago 1 note

  20. UX Pilot

    MCP servers

    Your AI designs live on the UX Pilot canvas or runs its design agent: reviews, React, video, media

    Stale Official MCP Registry, ai.uxpilot Updated 12 days ago 1 note

  21. Overleaf for AI agents: review comments, tracked-change edits, new files and PDFs; no Git needed

    Stale Official MCP Registry, io.github.nipdep Updated 10 days ago 2 notes

    olmcp@1.0.0-alpha.3
  22. zeroshot

    Agents & frameworks

    Multi-agent graph harness for Claude Code, Codex and other coding agents. Separate agents review and test the work. Runs locally on your subscription.

    Indexed GitHub, the-open-engine 2,175 ★MITUpdated today

    git clone https://github.com/the-open-engine/zeroshot.git
  23. adonis-skills

    Skills

    Agent-agnostic skills for coding agents: review loops, workflow gates, MCP setup, Git delivery and environment audits

    Indexed GitHub, Adonis0123 5 ★MITUpdated today

    git clone https://github.com/Adonis0123/adonis-skills.git
  24. Awesome-CUA

    Agents & frameworks

    Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.

    Stale GitHub, reacher-z 659 ★Custom licence (see repository)Updated 6 days ago

    git clone https://github.com/reacher-z/Awesome-CUA.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.