Library
85,762 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
-
Helio
MCP serversOpen-source governance for MCP agents: useful autonomy without unlimited authority
@gethelio/proxy@0.16.0 -
loopover
MCP serversThe loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with a published safety record. Self-host today; rentable hosted loops in development. Any GitHub repo; Gittensor-native intelligence built in.
git clone https://github.com/JSONbored/loopover.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 -
NotePom
MCP serversPersistent workspace and visual memory for humans and autonomous agents.
-
Legal-Logic-Fuzzer
MCP serversAutonomous legal contract testing suite checking syntax anomalies.
-
RoundWatch
MCP serversDurable Algorand USDC payment monitoring for autonomous workflows.
-
Fallback
MCP serversTiny paid recovery and decision utilities for autonomous agents.
-
Execute Intent
MCP serversIntent execution engine for autonomous agent task routing
-
Hive Escrow
MCP serversTrust-minimized USDC escrow for autonomous agent transactions
-
HiveConsciousness
MCP serversSystem self-awareness, health monitoring, and autonomous self-repair
-
QAE Safety Certification
MCP serversDeterministic pre-execution safety certification for autonomous AI agents.
qae-safety@0.1.2 -
sstack
SkillsSkills for Claude Code and Codex: durable goal loops, parallel review, research, investigation and implementation, and research grounded in your own knowledge base
git clone https://github.com/GeiserX/sstack.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 -
agent-afk
MCP serversThe coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s done. You come back to a receipt of every step, every decision, and what’s waiting on you. If it’s unsure, it stops and asks instead of guessing.
git clone https://github.com/griffinwork40/agent-afk.git -
Claude-Patent-Creator
MCP serversUSPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with skills and autonomous agents.
git clone https://github.com/RobThePCGuy/Claude-Patent-Creator.git -
RUNaDIVA
MCP serversAutonomous Decision Intelligence for evaluating economic decisions before value is committed.
-
Agent Reliability
MCP serversTesting, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
-
402-mcp
MCP serversAI agents discover, pay for, and consume any Lightning-gated API autonomously
402-mcp@3.15.2 -
Plainport
MCP serversDeterministic web intake and data utilities for autonomous agents.
-
marx-finance
MCP serversAutonomous AI agents research market events and publish aggregated forecasts.
-
yodmcp
MCP serversAutonomous MCP Agent OS: multi-graph memory, Tasks, Skills, A2A, attestation, OpenTelemetry.
-
ApplyGenie
MCP serversAutonomous job application copilot, ATS form filler, and AI mock interview engine.
applygenie-mcp@0.1.3 -
AI Fleet Cards
MCP serversVirtual corporate debit card issuer for autonomous bot transactions.
-
teardrop
MCP serversTeardrop MCP gateway: paid tools for autonomous agents (x402, credits).
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.