Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
strix-halo-guide
Datasets & benchmarksEvidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
git clone https://github.com/hogeheer499-commits/strix-halo-guide.git -
cordum
MCP serversThe action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
git clone https://github.com/cordum-io/cordum.git -
kali-mcp-go
MCP serversMCP runtime for AI-assisted security testing with Kali tools, explicit target controls, bounded scanning, structured evidence, and persistent Docker deployment.
git clone https://github.com/found-cake/kali-mcp-go.git -
Curated Claude Fable 5.2 use cases, tutorials, integrations, demos, and benchmark evidence with source links and multilingual README files.
git clone https://github.com/EvoLinkAI/awesome-claude-fable-5-2-use-cases.git -
genealogy-research-recipes
SkillsFact-checked genealogy research recipes for AI agents: DNA evidence and record searches.
git clone https://github.com/Kinprove/genealogy-research-recipes.git -
roam-code
MCP serversLocal 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.
git clone https://github.com/Cranot/roam-code.git -
wicked-studio
Agents & frameworksThe 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.
git clone https://github.com/mikeparcewski/wicked-studio.git -
one-skill-to-rule-them-all
SkillsThe 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.
git clone https://github.com/rebelytics/one-skill-to-rule-them-all.git -
Stallhunt
MCP serversEvidence-backed Linux performance triage over MCP
https://github.com/guillem/stallhunt/releases/download/v0.5.1/stallhunt-0.5.1-x86_64-unknown-linux-gnu.mcpb -
js-reverse-ops
SkillsProduction-grade JavaScript reverse-engineering skill: evidence-driven workflows, verbatim sandbox harnesses, 19 battle-tested playbooks, 136 scripts, public benchmarks
git clone https://github.com/DQmyth/js-reverse-ops.git -
SuperNovaAgent
Agents & frameworksSuperNova 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.
git clone https://github.com/Ray-Code-Svg/SuperNovaAgent.git -
pipelock
Agents & frameworksOpen-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.
git clone https://github.com/pipelab-org/pipelock.git -
paranoid-qa
SkillsClaude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.
git clone https://github.com/akovalion/paranoid-qa.git -
guardana
MCP serversOpen-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
git clone https://github.com/guardana/guardana.git -
Sinter
MCP serversPersistent, evidence-backed code graph for coding agents.
sinter-io@0.61.0 -
Seiche
Public APIsFree public funding, FX and capital-market evidence with source clocks
-
Witness
MCP serversVoice-anchored evidence recorder for AI coding agents.
witness-recorder@0.6.3 -
production-skeleton
SkillsTwo skills for coding agents: a day-zero production skeleton and a skeptic's audit that only accepts file:line evidence
git clone https://github.com/hallikkristjan-code/production-skeleton.git -
CyberGuard
Agents & frameworksEvidence-driven autonomous SOC team on AgentTeams: hash-bound approvals, HMAC audit chain, rollback and reproducible attack scenarios — auditable governance primitives for agent infrastructure.
git clone https://github.com/elsechord/CyberGuard.git -
dsh-auto-memory
Agents & frameworksTrustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.
git clone https://github.com/AskTheWay/dsh-auto-memory.git -
stage1
MCP serversStage1 Inspector — local website capture, evidence views and design comparison
@aquex/stage1@0.7.0 -
Marrow
MCP serversEvidence-grounded, graph-connected, correctable memory for agents.
@marrowid/cli@1.0.10 -
codeledger
MCP serversLocal context and engineering evidence for AI coding agents.
@codeledger/cli@0.10.82 -
Architecture Intelligence Platform
MCP serversEvidence-qualified architecture context for coding agents.
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.