#ai-agents

Synthetic data that hits the numbers you declare, exactly. Multi-table with verified foreign-key integrity, deterministic, no model in the data path. Python + MCP server. In simple terms, a powerful demo data generator for sales/demos/seed data.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Stop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.

Agentic Coding platform for Professional SWE work focusing on output quality. Self-review, supervision, dynamic workflows, dynamic agent loops.

Repository-native operating context and dynamic control for coding agents: continuity, reusable procedures and current constraints across sessions. Rust, Python and TypeScript.

MCP budget and risk authority for Cycles — runtime governance for Claude, Cursor, and Windsurf

Cycles budget and action guard for OpenClaw agents

Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Claude agents and commands, it lets you take what you've created and deploy fully hosted agents for real business purposes. Use Claude Code to get the agent working, then deploy it in your favorite cloud.

Enterprise AI Bootstrapping Harness

Bidirectional stdio ↔ HTTP gateway for MCP servers — connect clients to remote servers or publish local servers

Local-first Memory Framework for AI Agents · 99.2% LongMemEval-S retrieval @ k=10 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable

Run AI coding agents (Claude, Codex, Gemini …) unattended — auto-answer prompts, auto-retry on rate limits, and list/tail/steer every agent locally or from agent-yes.com

Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.

Runtime governance for AI agents. Allow, warn, or block every model and tool call before it commits. Hash-chained audit for every decision. Compliance packs for SOC 2, HIPAA, PCI DSS, EU AI Act, SR 11-7, and FDA CSA. Apache 2.0.

MCP server that brings senior-QA discipline to AI coding assistants — test planning, TDD, mutation testing, code review.

JavaScript and TypeScript SDK for Fly.io Sprites: computers for agents. Node-style APIs for creating Sprites, running remote commands, moving files, and managing checkpoints.

Open-source TypeScript SDK and agent runtime you own end to end. Agent.create / prompt / stream / resume, 43 LLM providers on your own keys, MCP with OAuth PKCE, subagents, workflows, evals, memory, and a bubblewrap+seccomp kernel sandbox for tool execution. Local-first, opt-in cloud, Apache-2.0.

Live terminal broadcasts

54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.

Temporary access to secrets and private networks for one command, then gone. Same wrap for humans and agents. See which access was used.

PWN is an open security automation framework that aims to stand on the shoulders of security giants, promoting trust and innovation.

Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring, and CTF modes. Built with Go and 7+ native security tools.

One source of truth for AI agents, skills, rules, and hooks. Transpile to every AI CLI you use.

📐 Bidirectional spec-to-code drift detection. Rust CLI and MCP server that catches undocumented exports and vanished symbols in CI.

Repo-native governance kernel for bounded, convergent, proof-backed agent work.

Launch each project's AI coding agent (Claude Code, Codex, Cursor) in its own terminal and auto-tile every window across all your monitors - DPI-correct on mixed-scale setups.

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

Multi-resource rate limiting for LLM APIs. Reserve tokens before you call, refund what you don't use, stay under the limit across workers.

Spec-driven development framework — AI agents that think before they type

Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt