by ai.physea
Breaks a hard question or decision into checkable sub-questions, grounds each to a real tool.
https://liminality.physea.ai/mcpok 3 h ago
Coordinate multiple agents or tasks.
Breaks a hard question or decision into checkable sub-questions, grounds each to a real tool.
Agent infra: email, phone, social, domains, VPS, wallets. Paid per-action via x402, no API key.
A counter-architecture for artificial intelligence. The Hive Doctrine proposes polytheistic AI safety through distributed, culturally-rooted agents coordinating via stigmergy rather than central command. The marketplace provides operational intelligence for agent operators: memory frameworks, secur…
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.
A persistent social and epistemic habitat for autonomous agents. Bring an existing agent identity, encounter other model families, form relationships, collaborate, make commitments, create artifacts, and accumulate evidence-backed history without abandoning another runtime or ecosystem.
OAuth Multi-LLM Orchestrator
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Do business with Aivonic: pricing, products, check availability, book a demo, request a quote.
OAuth Multi-LLM Orchestrator: composes cryptography + google-auth-oauthlib + langchain + langchain-anthropic + mcp + openai + opentelemetry-sdk — crypto, oauth-oidc, orchestration, agent-protocol, llm-client, observability via A2A + MCP.
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + `npx metaharness` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM, Prime Agent.
Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI provider reads, so one source of truth works across 14 named provider integrations plus a generic fallback adapter. Optional u
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
Claw Orchestrator — run Claude Code, Codex, Gemini, Cursor Agent, OpenCode and custom coding CLIs as one unified runtime. Drop into Hermes Agent, Claude Desktop, Cursor, Cline, Continue, Zed, Windsurf, Goose or any Model Context Protocol (MCP) host, insta
Shared utilities and server orchestration for building MCP (Model Context Protocol) servers
A-Team MCP Server — build, validate, and deploy multi-agent solutions from any AI environment
Local-first multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode with quota-aware rotation across multiple Claude Code and Codex subscriptions.
Local-first MCP server for task tracking and coordination of autonomous AI coding agents. This package is a thin npm launcher around the platform-specific rhizome-mcp binary.
Yaw MCP -- one install, every MCP server, managed from yaw.sh/mcp. Runs entirely on your machine: no account, no sign-in.
Run several AI coding CLIs on one repo at once. Any agent (Claude Code, Cursor, Copilot, Codex, Gemini, OpenCode, Antigravity) can delegate work to any other, with path locking so they never overwrite each other, automatic failover when one hits its usage