#ai-agents

Terminal-first relay for paired AI coding agents (Claude + Codex), driven by structured workflows.

Agentic Runtime

Most tools check the code your agent wrote. nullius checks how it got there — citations, session journals, weakened tests.

FastroAI wraps PydanticAI with production essentials: cost tracking in microcents, multi-step pipelines, and tools that handle failures gracefully.

Local-first MCP server for Google Health API v4 (Fitbit + Pixel Watch) — Claude/Cursor/Hermes

Adobe Photoshop adapter for the DCC Model Context Protocol (MCP) ecosystem — bridges MCP tools to Photoshop via UXP WebSocket

An AI-agent behavior profiler using a maze runner, hide and seek game.

Free local web search/extraction router for AI agents. Go CLI + MCP, BYOK/free-first routing, keyless DDGS/Scrapling fallback, setup writers and client guides.

Utilities for Android emulators, iOS simulators and real devices: launch, stream, control, record and automate them from a desktop app, TUI and CLI

Dependency assurance software for Go. A deterministic, local source of truth about your dependencies - what's in them, how they're licensed, how to call them, and which known vulnerabilities your code actually reaches. Developers query it from the CLI with human-readable output; AI coding agents get JSON.

Git-native session capture for AI coding agents — rewind, resume, and audit every AI interaction

Shrinks your AI agent's tool output so it burns fewer tokens, without changing what the agent reads. Lossless by default, no decode step.

Every Wade does the dirty work so the heroes don't have to. Branches, worktrees, context, PRs — handled.

MCP server for running heterogeneous AI agents and shell commands in local disposable OpenSandbox containers

One Go binary that runs Ansible, Terraform, OpenTofu, Bash, PowerShell, Python, and Go across a fleet. Live host-by-task matrix, hash-chained audit you can verify offline, enforced approvals. No Kubernetes, no Postgres, no Redis. Migrate from AWX, Semaphore, Ascender, or Ansible Automation Platform in one command.

Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results

Provider-agnostic TypeScript agent SDK — pluggable providers, built-in tools, skills, memory, and MCP

Federated, evidence-first retrieval for personal AI agents

Terminal code review for AI coding agents. Live diffs, comments the agent answers, PR review, MCP built in.

31 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama extraction by default. MIT, 1,000 free credits.

Route inference calls to different providers based on a fallback condition, or a routing rule you define.

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.

End-to-end encrypted memory for AI agents — portable, yours forever.

Persistent, provider-neutral memory for Codex, Claude Code, OpenCode, Pi, and MCP coding agents.

The portable trust harness for AI

Zero-dependency Web Crypto suite & Model Context Protocol (MCP) server for AES-256-GCM, RSA-4096, and AI agent security.

Self-hosted AI knowledge agent — TypeScript, Bun, MCP. Own your data, run your own brain.

Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limits reset—across tmux, Zellij, VS Code, and desktop apps.

Local context-compression layer for agent tool outputs. Claude Code PostToolUse hook or generic filter, single Go binary.

Extended Memory Layer of Coding AI