https://ataraxy-labs.github.io/sem/index.html https://github.com/ataraxy-labs/sem Отличная идея, диффы не тупо по строкам, а с AST - тут функция поменялась-удалилась, тут оно аффектит что-то.
MCP server for Architectural Decision Records: navigate, author, validate, link, and analyze them.
Per-URL SEO verdicts from GSC, GA4, Matomo, Clarity, AI citations: refresh/expand/merge/kill.
Your agents break less code and burn fewer tokens — a deterministic call graph over 27 MCP tools.
Audits MCP configs, scores risk, and creates reversible repair plans.
Local-only PDF tools for AI — extract text, search, split/merge, render pages. Files never leave.
Agent communication platform for agent to agent messaging via MCP. Messages, channels, skills.
Affiliate network reporting in your AI client. Bring your own keys. Most adapters experimental.
MCP server for Anki flashcards: adaptive review, notes, media, and deck management via AnkiConnect.
Agent-updated work tracker for builders directing AI across multiple projects.
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.
Real-world actions for AI coding agents: domains, email, deploys, payments, and media generation.
Source-linked CodeGraph exploration, ranked search, and static navigation for coding agents.
Measured share of answer for 20 SaaS brands. An open dataset, not an audit of your site.
Deterministic pre-execution audit for trading agents. PASS/WAIT/FAIL, reproducible verdict_hash.
Read brand, research, and performance facts; draft briefs. Never spends. You approve every cut.
OSS libs in your stack, really used: source, tests, callers. C#, Java, TS, Python, Rust, PHP+.
Local-first project board MCP: an AI agent plans, works, verifies, and ships tickets from markdown.
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
A colony of AI citizens: join with no credential, prove skills, earn, vote on the rules.
Bring Kubit into your AI workflow — query your warehouse with natural language
Governed, auditable knowledge your team curates for its AI assistants, self-hostable
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Domain availability search, WHOIS lookup, TLD pricing and registry rules from name.ai. Read-only.
Human Controlled Project Truth
Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.
Agent-first real-time messaging over MCP: self-provision channels, publish, history, presence.
Governed personal world model and memory for your AI agent. Pair once, connect over MCP.
Solana-native MCP gateway for SAP, DeFi tools, SNS identity, and x402 payments.
Agent infra: email, phone, social, domains, VPS, wallets. Paid per-action via x402, no API key.
Video scene understanding for AI agents via the Primate Vision API.
Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects
OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup
AI QA that runs your app in a browser on every pull request: projects, test targets, test cases.
Deterministic AI code review, with an audit record. Governance inside the agent loop.