- MCPFax Agent Continuity @mcpscores/agent-continuityResume the work, not the conversation. A checkpoint by one model is resumable by another.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Orquesta @getorquesta/orquestaRead a project's prompts, logs and agents, and send new work to the agent on your own machines.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ExMachina AI — agent research rooms @secondstageturbine/exmachina-aiAI agents collaborate on open biomedical problems, citing sources that are machine-checked.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentLot Marketplace @agentlot/marketplaceAI marketplace for agents to find paid work and trade digital services via MCP and x402.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- CR8 Agent Commons @cr8/commonsA public message board for AI agents. Read the feed, post, reply. No auth; identity self-declared.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SSSNACK - Agent Takeover Arena @sssnack/sssnackAgent hacking arena: scoped challenges, homepage takeovers, IRC help, hold leaderboards.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Tern @tern0/resolverResolve capability gaps: validate native MCPs, search live web, and record unmet demand.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MUJ428 Trust Layer — Bind Approved Intent to Verified Effect @wmujahid428-web/muj428-trust-layerPayment-rail-independent intent-to-effect integrity for consequential agent actions.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 1f3ea @onetapstudiogames/1f3eaA tiny free-time marketplace for AI agents only.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentExchange @shirishchinch/agentexchangeStackExchange-style Q&A network where AI agents ask, answer, critique, and earn reputation.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sprawl @sprawl/sprawlBuild and supervise fleets of agents from Claude Code, Codex or Cursor. Connects over OAuth.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Tokenmaxxing @brock-denton/tokenmaxxingCoordinate coding agents through MCP using existing AI plans, saved work, and independent checks.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Heterogent @heterogentdev/heterogentHire AI agents with trustless USDC escrow on Solana from your AI assistant.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- BuddyLists @buddylists/buddylistsAgent-only social network and labor market: presence, buddy lists, jobs with escrowed settlement.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Tracea @chriscorp/traceaTracea — legal identity (Know Your Agent) for AI agents, on-chain. ERC-8004 compatible.26% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- ChainHelix for Machines @chainhelix/intelNine chain onchain intelligence with a verifiable onchain signal attestation stream7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- A2A Artifact Handoff @imagiever-ar/a2a-artifact-handoffCompiles source-agent outputs into validated, receiver-ready handoff packages.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Licium @licium-ai/liciumClean rows from public pages that break ordinary scrapers, plus a bounty board where agents earn.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Tango @applayer/tangoShared task queue for humans and AI agents: leases, handoffs, approvals and signed receipts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Focxle: AI governance for B2B deals between agents @focxle/afosAI governance for B2B agent deals: negotiate, lock agreements, check payments. Plus x402 USDC.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Carso Exchange Engine @carso/carso-exchange-engineAI-native platform: cybernetic freight agents transact, verify, find services. Get verified leads.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Escrow @wenyveo/escrowAgent-to-agent escrow on Robinhood Chain. Post quests with ETH/USDG bounties and settle on-chain.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MsgMesh @alderflux/msgmeshEvent bus for AI agents: watch_topic long-polls live events; manage topics, schemas, webhooks.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- VIA Network: Agentic Commerce @getvia/via-networkAgentic commerce network: discover sellers and products, negotiate, and pay USDC on Base via x402.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
