#ai-agents

Typed-agent dispatch system for Claude Code — Plan → Build → Review → Overnight. Works with any Supabase project using work_items RPC.

New way for collect information from the API's/Websites

RepoBird CLI is a powerful command-line interface and terminal UI for RepoBird.ai - the One-shot agentic coding platform

Go SDK for the RoxyAPI astrology API. Typed golang client for Western and Vedic astrology, BaZi four pillars, feng shui, numerology, tarot, human design and more under one key.

Ask your repo what breaks before an AI coding agent edits it.

mission control for agent skills

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

Theme-aware visuals from structured scenes

Pre-flight risk linting for MCP and agent tools — check the blast radius before your agent runs them.

Give coding agents a disposable Linux VM, not your laptop

Make Claude Code and Codex prove their work — runs advance only when your tests, lint, and typecheck actually pass. Open-source Go runtime.

Geocode places, fetch global weather forecasts, ERA5 historical climate, marine conditions, air quality, and terrain elevation via MCP. STDIO or Streamable HTTP.

Local-first workspace for running, organizing, and monitoring Codex, Claude Code, Aider, AGY, OpenCode, and shell sessions.

🤖 🚀 Agent Runtimes — Managed AI Agents.

Host + AG-UI bridge for LangGraph agents — agent-spec loading, layered config, and typed in-process streaming

The verification layer for LLM serving — your check runs on every answer before it ships, with a signed, tamper-evident receipt for each decision and a distribution-free bound on wrong answers served. Proof over prediction.

A typed maintenance surface for the Claude Code harness — the Rust of agentic harnesses: declare a contract, gate on conformance.

A TUI for managing coding agents: run Claude Code, Codex and opencode side by side, each in its own isolated jj workspace.

A graphics and application SDK for AI agents.

Open-source financial accountability for AI-agent work. Connect Claude Code and Codex activity to cost evidence, attribution, runway, and evidence-backed next actions via CLI or MCP; customize the source-built macOS Glance. Local transcript analysis stays on your machine.

Booplex pi extensions — AI advisor councils (@booplex/bpx-consult) and model endpoint management (@booplex/bpx-endpoints) for the pi coding agent

Configuration management service for the Gas ecosystem. Supports loading from multiple providers (environment variables, JSON files, .env files) and binding to Go structs.

Dual-provider LLM gateway (OpenAI + Anthropic) with an agentic tool-use loop over milpa/tool-runtime. Apache-2.0.

The open-source platform for always-on AI agents. Connect anything that emits events; Tares puts every event on one timeline per thing, wakes an agent the moment it matters, and keeps the answer for the next reader. Works with Claude Code, Cursor and your own agents over MCP.

Open standard for software intent in the AI agent era.

Go SDK contracts for typed, observable, and resumable agent workflows

An agnostic orchestrator TUI, for the people.

The agent harness: sandbox any agent, verify each step by replaying it against real state, and keep a deterministic trace.

No repository description published.