MCP servers and skills: search, filter by where they run, and compare.
1–24 of 1,308 tools for “verifiable-ai”
Clear allLocal-first, append-only, tamper-evident memory for AI agents via MCP.
Node.jsMIT★ 1Few starsNo key
Verifiable-AI MCP server: mint and verify offline action receipts, run reproducible GDPR checks. Local-first, no telemetry.
Node.jsMITFew starsNo key
VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked
PythonMIT★ 325No key
Pass the baton, not the blur. Two-way session handoff protocol for AI coding agents.
SkillMIT★ 2Few starsNo key
The verifiable AI coding agent : provider-agnostic, MCP-native, tamper-evident ledger
PythonMIT★ 5No key
Verifiable-reward RL environments and evals for scientific domains, starting with HLA/immunogenetics
Hosted by authorApache-2.0Few starsNo key
The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the o
SkillApache-2.0★ 122No key
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces
OfficialSkillMIT★ 40k in collectionNo key
Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP · multi-model · Windows/CJK · listed in awesome-opensource-
PythonMIT★ 53No key
Verifiable backtests for AI-built trading strategies: deterministic engine, reproducible results.
Hosted by authorNo licenseFew starsNo key
Autonomous Governance Theory (LGD) · Independent Third-Party Evaluation for the Age of Autonomous Agents | 凡自治之物 - LGD 治理学 - 独立评测（Independent Evaluation）
SkillCC-BY-4.0★ 1Few starsNo key
AI 会编数据、假报完成、换人就失忆？7 个实战方法论技能，让 AI 干活可验证、可追溯。Practical skills that make AI honest - no fabrication, no fake completions, no lost context.
SkillMIT★ 1Few starsNo key
Skill and Agent Prompt Audit Tooling (scanner) | 技能与提示词安全审计（AI 技能审计器）
SkillApache-2.0★ 1Few starsNo key
The open .laplaspack format — portable, verifiable AI memory. Spec + LMD grammar + zero-dependency reference reader.
SkillMIT★ 8No key
Give AI proven facts — a cryptographically verified truth layer for agent AI, built on ZK proofs, selective disclosure, and on-chain provenance.
MCPLink only★ 1Few stars
SkillMIT★ 1Few starsNo key
SkillMIT★ 5No key
PythonMIT★ 5No key
Verifiable AI data scientist for CSVs and databases — SQL, statistics, ML, and visualization with claim-level evidence and reproducible artifacts.
PythonMIT★ 2Few starsNo key
Verifiable AI agent for engine test data: every number in the report traces back to a reproducible computation.
PythonMITFew starsNo key
The glass-box game engine for AI agents — every state visible, operable, and verifiable. AI builds, tests, and iterates games autonomously.
SkillMIT★ 3Few starsNo key
IGL, Identity Governed Logic: a governed identity graph, policy engine and signed audit chain for AI agents. Every answer cites its records; every action leaves a receipt. Runtime, platform API, MCP s
Node.jsApache-2.0★ 1Few starsNo key
Open standard for verifiable AI agent identity and authority. One signed JSON file at /.well-known/agent-passport.json, keyed in DNS. Verifier, spend caps, signed receipts, CLI and MCP server. MIT.
SkillMIT★ 1Few starsNo key
Open-source verification layer for AI agents — signed receipts, fail-closed policies, deterministic proof. Local-first, zero telemetry.
SkillApache-2.0★ 3Few starsNo key
Who stands behind it
