#ai-agents

Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compatible app before requests leave your machine, tool-call arguments included, then restores them in the reply. Local detection, zero telemetry.

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

Decode, search, validate, and crosswalk US medical codes — ICD-10-CM, ICD-10-PCS, HCPCS Level II, RxNorm — over a bundled offline index via MCP. STDIO or Streamable HTTP.

Agent coordination MCP server — shared blackboard, decision tracking, and context assembly

Blender addon for the DCC Model Context Protocol (MCP) ecosystem — embeds a Streamable HTTP MCP server directly inside Blender

Go-native cli proxy that reduces token usage

Constraint-driven runtime for TypeScript. Declare requirements, let the runtime resolve them.

Composable Go interfaces for running AI agent sessions

Self-hosted OpenAI/Anthropic-compatible gateway: give each AI agent run a dollar budget, enforced before the provider, with a payload-free per-run cost record.

Automate your mobile devices with natural language commands - the counterpart android app for the mobilerun framework

Mandrel is an orchestration and harness for agentic AI coding. It ships a system prompt, personas, a two-tier skill library, baseline rules, slash-command workflows, and a GitHub-backed orchestration engine — distributed as a Git submodule into your project's .agents/ directory.

The runtime reliability layer for AI agents.

A fast, cross-platform build system and task orchestrator for polyglot monorepos. One statically linked Go binary, config as code, no second toolchain to install.

Your agent machine needs your logins. Pantry ships them sealed. Opt-in AES-256-GCM browser session and secret sync for AI agent hosts.

🚢 Run Claude Code's ⚙️ Dynamic Workflows, 👥 Agent Teams & ⚡ Subagents on any third-party model — DeepSeek · GLM · Kimi · Qwen … or your Codex subscription. No Anthropic subscription needed. ｜ 🚢 让 Claude Code 的 ⚙️ Dynamic Workflow、👥 Agent Team、⚡ Subagent 用上任意第三方模型 — DeepSeek · GLM · Kimi · Qwen…… 或你的 Codex 订阅,无需 Claude 订阅

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

Trust-aware Nostr MCP server for AI agents and humans. Verification, proximity, and access woven into every interaction.

Conversational-AI framework for Go.

A local workbench for agents doing continuous work across sessions, commands, human input, and external events.

A unified CLI for discovering and invoking tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC

A local orchestrator that takes your coding agent from spec to pull request, stopping only when a decision is yours.

Опис репозиторію не опубліковано.

Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.

Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude Code, Codex, Gemini) do the work, and nothing goes out until you approve. Open source, runs on your machine.

📦 Prepare selected marimo notebook states once, then consume verified exports from Python, TypeScript, agents, or custom applications

CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

Configurable tool bundle for AI coding agents — use via MCP server, CLI, or agent skills. npm wrapper for the Rust binary.

Official MUXI SDK for Go

Runtime failure prevention for AI agents. Prevents predictable failures before they reach the execution layer

All-in-one workspace for AI coding agents