Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
odai
SkillsAI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
git clone https://github.com/orziz/odai.git -
Sequesign
MCP serversCryptographically verifiable receipts of an agent's delegated work, verified offline.
@sequesign/mcp@0.4.1 -
opendraft
Agents & frameworksThe open-source agent system that writes research papers with verified citations. Every citation checked against Crossref, OpenAlex and Semantic Scholar.
git clone https://github.com/federicodeponte/opendraft.git -
awsl
Agents & frameworksCodex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees
git clone https://github.com/XhinLiang/awsl.git -
HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, Contact Screening, Stocks, Crypto, News
MCP servers75 paid agent tools: website audits and research; BM25, MiniLM vector and hybrid discovery are free.
-
openkakao-cli
Agents & frameworksKakaoTalk CLI for macOS and AI agents: send, read, react, search, back up and clean up chats through the official app. Login-free, verified sends in 0.5 s.
git clone https://github.com/JungHoonGhae/openkakao-cli.git -
vaspera-pm
MCP serversVerify docs against code, detect drift, and generate verified specs (MCP server).
vaspera-pm@2.15.0 -
Tourmind-Booking-Skills
SkillsAI agent skills for end-to-end hotel and flight booking—compare live hotel rates across leading OTAs and suppliers, search and verify real-time airfares worldwide, book stays and flights, and manage reservations, hotel cancellations, and payments via the TourMind API.
git clone https://github.com/tourmind-com/Tourmind-Booking-Skills.git -
loop.js
Agents & frameworksA loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.
git clone https://github.com/loop-js/loop.js.git -
Homo Universalis — HU-DIAMOND v1.1 Cryptographic Verifier, W3C VC 2.0 & AST Kintsugi MCP
MCP serversZero-auth Notary & AST: RM(1,3), RFC 6962, W3C VC 2.0, ROS 2, 3-Level Mind & A2A-MCP Bridge.
-
agent-envelope-mcp
MCP serversNeutral MCP server for AgentEnvelope authority: sovereign verify + vault verify/lookup/mint.
agent-envelope-mcp@1.0.1 -
AIFeed
MCP serversVerify signed AIFeed permissions, fetch token-budgeted markdown, and verify assets for AI agents.
aifeed-mcp-server@1.0.0-draft.2 -
Semantic Geometry
MCP serversDeterministic verifier: LLM proposes, graph verifies. Sub-ms, offline, 0 tokens.
-
conductor
MCP serversVerified tool calls for Claude Code: verify, retry and fallback over hermetic claude calls.
@fainir/conductor@0.4.1 -
Agentlas-OS
Agents & frameworksThe Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor.
git clone https://github.com/agentlas-ai/Agentlas-OS.git -
styleseed
SkillsOpen-source design-method engine for Claude Code, Codex & Cursor. One agent skill with 22 internal workflows for fixed design judgment, multiple grammars, semantic palettes, reference compilation, and evidence-verified UI. MIT.
git clone https://github.com/bitjaru/styleseed.git -
Credda Trust
MCP serversCheck a counterparty's verifiable Credda trust record; verify or present signed credentials.
@credda/mcp-server@0.1.3 -
ProofStream
MCP serversDispatch a human verifier to physically verify anything in the real world. For AI agents.
proofstream-mcp@0.1.1 -
stamp
MCP serversConcierge MCP for agentic workflows: verified time + drift, uuid, diff, calc, attest, verify.
stamp-mcp@0.6.1 -
vouch-mcp
MCP serversSign and verify W3C Verifiable Credentials so AI agents can cryptographically authorize actions.
vouch-mcp@3.0.0 -
Agentic Terminal Directory
MCP serversVerified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
-
data-access
MCP serversVerified federal funding intelligence with sealed provenance; verify any figure at no charge.
-
carso-exchange-engine
MCP serversAI-native platform: cybernetic freight agents transact, verify, find services. Get verified leads.
-
humancollab
MCP serversTrust layer between AIs and humans: signed, domain-verified information in a public, verifiable log.
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.