- Myco: Agent-First Cognitive Substrate @battam1111/mycoAgent-first cognitive substrate: 20 verbs + 50 lint dims over a self-validating graph.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.66 GitHub stars.
- Nora @solomon2773/noraOperate self-hosted OpenClaw and Hermes agent fleets on Docker or Kubernetes from MCP clients.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.57 GitHub stars.
- Jev Use @shitianfang/jev-useTyped yes/no, pick-one and score judgments from Jev in one batched call; typed escalation back.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.56 GitHub stars.
- arifOS @ariffazil/arifos-mcpConstitutional AI governance server with 5-organ Trinity and enforced floors F1-F13.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.53 GitHub stars.
- Aaa @ariffazil/aaa-mcpConstitutional AI Governance with 13 enforced floors (F1-F13) and tri-witness consensus for LLMs.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.53 GitHub stars.
- PIO Agent @jl-codes/platformio-mcpBuild, inspect, flash, and monitor PlatformIO firmware projects with policy-controlled tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.52 GitHub stars.
- Proximo — the Proxmox MCP you can hand the keys @john-broadway/proximo-proxmoxThe Proxmox MCP you can hand the keys: VE/PBS/PMG/PDM. Plan, prove, undo, diagnose. MCP/A2A/API.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.52 GitHub stars.
- ProofFlow @hyperion-gpu/proofflowAudit infrastructure for AI coding agents with evidence-backed review and policy gates.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.49 GitHub stars.
- Floom @floomhq/floomDeploy Python functions as web apps with auto-generated UI, REST API, and shareable links.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.46 GitHub stars.
- DollhouseMCP @dollhousemcp/mcp-serverOSS to create Personas, Skills, Templates, Agents, and Memories to customize your AI experience.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.45 GitHub stars.
- Agent MCP Gateway @roddutra/agent-mcp-gatewayOn-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.41 GitHub stars.
- Kage @kage-core/kageVerified memory for coding agents: claims cited against code, stale withheld, savings receipts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.40 GitHub stars.
- Signet MCP Tools @prismer-ai/signet-mcp-toolsMCP server exposing Signet cryptographic signing, verification, and content hash tools over stdio.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.39 GitHub stars.
- OCM @ocm-mcp-server/ocm-mcp-serverGuardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.37 GitHub stars.
- Cartographer @beppetemp/cartographerGovernance MCP server for agent-maintained knowledge bases (OKF): git-backed writes, search, lint.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.37 GitHub stars.
- Grantex @mishrasanjeev/grantexOAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.33 GitHub stars.
- AgentGate @agentkitai/agentgateHuman-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.33 GitHub stars.
- JanuScope @giancarloerra/januscopeLocal MCP proxy for tool restrictions, response redaction, audit logs, and database schema context.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.32 GitHub stars.
- Graqle @graqle/graqleDev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
- agent-bom @msaad00/agent-bomSecurity scanner and graph for agentic infrastructure — agents, MCP, runtime, and blast radius.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.31 GitHub stars.
- Janee @rsdouglas/janeeSecure secrets proxy for AI agents — manages API keys so agents never see raw credentials.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.30 GitHub stars.
- MCP Memory Gateway @igorganapolsky/mcp-memory-gatewayPre-action gates that block AI agents from repeating known mistakes.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.28 GitHub stars.
- RLHF feedback loop @igorganapolsky/rlhf-feedback-loopRLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.28 GitHub stars.
- Humane Proxy @vishisht16/humane-proxyAI safety middleware — detects self-harm and criminal intent in LLM prompts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.28 GitHub stars.
