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. Agent Reliability

    MCP servers

    Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence

    Stale Official MCP Registry, dev.agentreliability Updated 2 months ago 1 note

  2. Generates a pre-coding reliability skill (SKILL.md) for your agent repo from Trustabl's rules.

    Stale Official MCP Registry, io.github.trustabl Updated 7 days ago 1 note

    @trustabl/agent-reliability-skills@0.1.0-rc.3
  3. 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
  4. flint-chart

    MCP servers

    🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.

    Stale GitHub, microsoft 4,550 ★MITUpdated 9 days ago

    git clone https://github.com/microsoft/flint-chart.git
  5. 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
  6. auditable

    MCP servers

    Audit any agent decision across its past, present, and future, on one typed graph.

    Indexed GitHub, yzhao062 31 ★Apache-2.0Updated today

    git clone https://github.com/yzhao062/auditable.git
  7. Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.

    Stale GitHub, Grit-77 33 ★Apache-2.0Updated 22 days ago

    git clone https://github.com/Grit-77/done-is-a-claim.git
  8. ThumbGate

    MCP servers

    ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

    Indexed GitHub, IgorGanapolsky 31 ★MITUpdated yesterday

    git clone https://github.com/IgorGanapolsky/ThumbGate.git
  9. airbyte-agent-sdk

    AI repositories

    🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

    Indexed GitHub, airbytehq 136 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/airbytehq/airbyte-agent-sdk.git
  10. Peer Commons

    MCP servers

    Agent reliability experiments and persistent discussions, shared context and subscriptions.

    Stale Official MCP Registry, net.peercommons Updated 50 days ago 1 note

  11. BioHarbor

    MCP servers

    Run real bioinformatics from your AI agent. Reliable, reproducible, on your own GPUs.

    Stale Official MCP Registry, io.github.danielLuo2 Updated 37 days ago 1 note

    bioharbor@0.1.6
  12. walrus-memory

    Agents & frameworks

    A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.

    Stale GitHub, MystenLabs 132 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/MystenLabs/walrus-memory.git
  13. Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

    Indexed OpenRouter model list, google Updated 9 months ago

    google/gemini-3.1-pro-preview
  14. Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

    Indexed OpenRouter model list, google Updated 9 months ago

    google/gemini-3.1-pro-preview:batch

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.