InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

1,253 results Clear search and filters
  1. strix-halo-guide

    Datasets & benchmarks

    Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

    Stale GitHub, hogeheer499-commits 373 ★MITUpdated 8 days ago

    git clone https://github.com/hogeheer499-commits/strix-halo-guide.git
  2. cordum

    MCP servers

    The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

    Indexed GitHub, cordum-io 510 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/cordum-io/cordum.git
  3. kali-mcp-go

    MCP servers

    MCP runtime for AI-assisted security testing with Kali tools, explicit target controls, bounded scanning, structured evidence, and persistent Docker deployment.

    Stale GitHub, found-cake 25 ★MITUpdated 15 days ago

    git clone https://github.com/found-cake/kali-mcp-go.git
  4. Curated Claude Fable 5.2 use cases, tutorials, integrations, demos, and benchmark evidence with source links and multilingual README files.

    Indexed GitHub, EvoLinkAI 84 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/EvoLinkAI/awesome-claude-fable-5-2-use-cases.git
  5. Fact-checked genealogy research recipes for AI agents: DNA evidence and record searches.

    Indexed GitHub, Kinprove 32 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/Kinprove/genealogy-research-recipes.git
  6. roam-code

    MCP servers

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

    Stale GitHub, Cranot 516 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/Cranot/roam-code.git
  7. wicked-studio

    Agents & frameworks

    The ADE (agentic development environment) for running a team of coding agents: start a job with a chat, answer what needs you with the evidence, and build apps and dashboards over your data in a chat.

    Stale GitHub, mikeparcewski 173 ★MITUpdated 7 days ago

    git clone https://github.com/mikeparcewski/wicked-studio.git
  8. The meta-skill that improves your skills, including itself. Turns the corrections, judgement calls and repeated workflows of your sessions (autonomous or human-led) into small skill updates and new skill candidates, each with its evidence and reason. Nothing touches a skill until you approve it. Augmented Expertise in practice. CC BY 4.0.

    Indexed GitHub, rebelytics 3,925 ★CC-BY-4.0Updated 2 days ago

    git clone https://github.com/rebelytics/one-skill-to-rule-them-all.git
  9. Stallhunt

    MCP servers

    Evidence-backed Linux performance triage over MCP

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

    https://github.com/guillem/stallhunt/releases/download/v0.5.1/stallhunt-0.5.1-x86_64-unknown-linux-gnu.mcpb
  10. Production-grade JavaScript reverse-engineering skill: evidence-driven workflows, verbatim sandbox harnesses, 19 battle-tested playbooks, 136 scripts, public benchmarks

    Stale GitHub, DQmyth 17 ★MITUpdated 8 days ago

    git clone https://github.com/DQmyth/js-reverse-ops.git
  11. SuperNovaAgent

    Agents & frameworks

    SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can produce visible artifacts, runtime receipts, replayable evidence, and controlled workspace execution.

    Stale GitHub, Ray-Code-Svg 187 ★Apache-2.0Updated 4 months ago

    git clone https://github.com/Ray-Code-Svg/SuperNovaAgent.git
  12. pipelock

    Agents & frameworks

    Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

    Indexed GitHub, pipelab-org 993 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/pipelab-org/pipelock.git
  13. paranoid-qa

    Skills

    Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.

    Stale GitHub, akovalion 16 ★MITUpdated 15 days ago

    git clone https://github.com/akovalion/paranoid-qa.git
  14. guardana

    MCP servers

    Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

    Indexed GitHub, guardana 225 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/guardana/guardana.git
  15. Sinter

    MCP servers

    Persistent, evidence-backed code graph for coding agents.

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

    sinter-io@0.61.0
  16. Seiche

    Public APIs

    Free public funding, FX and capital-market evidence with source clocks

    Indexed public-apis (GitHub list)

  17. Witness

    MCP servers

    Voice-anchored evidence recorder for AI coding agents.

    Indexed Official MCP Registry, io.github.wookat Updated 2 days ago 1 note

    witness-recorder@0.6.3
  18. Two skills for coding agents: a day-zero production skeleton and a skeptic's audit that only accepts file:line evidence

    Stale GitHub, hallikkristjan-code 12 ★MITUpdated 11 days ago

    git clone https://github.com/hallikkristjan-code/production-skeleton.git
  19. CyberGuard

    Agents & frameworks

    Evidence-driven autonomous SOC team on AgentTeams: hash-bound approvals, HMAC audit chain, rollback and reproducible attack scenarios — auditable governance primitives for agent infrastructure.

    Stale GitHub, elsechord 55 ★Apache-2.0Updated 26 days ago

    git clone https://github.com/elsechord/CyberGuard.git
  20. dsh-auto-memory

    Agents & frameworks

    Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.

    Indexed GitHub, AskTheWay 132 ★MITUpdated 3 days ago

    git clone https://github.com/AskTheWay/dsh-auto-memory.git
  21. stage1

    MCP servers

    Stage1 Inspector — local website capture, evidence views and design comparison

    Stale Official MCP Registry, ai.aquex Updated 15 days ago 1 note

    @aquex/stage1@0.7.0
  22. Marrow

    MCP servers

    Evidence-grounded, graph-connected, correctable memory for agents.

    Stale Official MCP Registry, id.marrow Updated 43 days ago 4 notes

    @marrowid/cli@1.0.10
  23. codeledger

    MCP servers

    Local context and engineering evidence for AI coding agents.

    Stale Official MCP Registry, io.github.codeledgerECF Updated 18 days ago 1 note

    @codeledger/cli@0.10.82
  24. Evidence-qualified architecture context for coding agents.

    Stale Official MCP Registry, io.github.michaelegner Updated 20 days ago

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.