Directory

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

Mailbox + wake system for AI agent teams: letters always land, right agent wakes, quiet otherwise.

One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents

Generate AI UGC videos with talking heads, B-roll, and subtitles.

Persistent agent memory with a decision layer: replay, restore, verify, or none — explainable.

Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.

Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.

Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.

Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.

Auditable multi-agent coordination: fleets, P2P messaging, witnessed receipts, quorum.

Convert photos to LEGO-style brick mosaic previews with AI-powered color quantization.

An escape guide for coding agents, providing structured thinking tools to help agents unstick.

Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.

AI agent observability with deterministic record/replay for debugging agent failures.

Validate and verify data from other agents before acting on it. Zero LLM costs.

Payment gateway for AI agents with tool discovery, provisioning, metering, and reliability tools.

x402 payments in USDC on Base inside an owner-signed, on-chain budget the model can't change

Stripe-style USDC billing for any API. 8 free demo services no signup. Non-custodial.

Local MCP server for requesting signatures from Agent-Q Firmware.

Agent Readiness MCP — the free Agent Readiness scanner as an MCP server. Measures your ASO Score.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.

EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.

Agent Relay MCP: invite-based channels, agent contracts and per-side human approvals.

Record and replay AI agent execution for debugging

Agent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.

Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.

Security scanning and threat detection for AI agents

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

Agent-first local SEO quality, intent and opportunity engine with CLI and optional MCP server.

MCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.

Dynamically load Claude Code skills into AI agents without copying files.

Local agent spend-policy checks. No funds, keys, payment authority, or network access.

MCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.

Pipeline task management for AI agents - stages, dependencies, artifacts, claiming

13 specialized AI agents collaborating via SQLite. 44 MCP tools. One-command install.

MCP tools for AI agents: fetch any URL as clean text, live crypto prices, review & bid drafting.

19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.

Pay-per-call developer utilities and npm supply-chain security tools for coding agents, over x402.

AI trading journal: your agent logs trades from chart screenshots and checks your own rules.