Search

ConnectOnion Studio — local test cockpit for ConnectOnion agents: create, run, QR, live logs, Copy-for-Claude diagnostics.

Auditable BDI (belief-desire-intention) agents with LLM deliberation — explicit beliefs, committed intentions, and a trace that answers 'why'

A portable, headless LLM Wiki — compile knowledge once, maintain it continuously. CLI.

Proof-of-done gate that makes AI agents prove a task is done before claiming it.

Database schema graph for AI agents — index your database catalog into a local graph, served over MCP

Database schema graph for AI agents — index your database catalog into a local graph, served over MCP

Measure whether the code an AI agent built matches the spec it was given.

Framework adapters that wire TryAgent human-in-the-loop guardrails into LangGraph, the Vercel AI SDK, and the OpenAI Agents SDK.

Query SQL databases in natural language using an AI agent. PostgreSQL, MySQL and SQLite.

AgentFeed CLI for sharing privacy-safe AI agent worklogs — never your code.

Pluk structured events from AI agent terminal output — classify, subscribe, and react to JSONL event streams

A local-first AI orchestration framework

AgentGuard CLI — the deployment gate that blocks unsafe AI agents in CI.

Pure-function policy matrix evaluator for AI coding agents (repo x capability x context -> deny/require_approval/auto_allow).

agentplane shared contract: Definition schema, registry models, interfaces

agentplane typed client + CLI

agentplane discovery service (standalone-capable)

EvoAgent — Unified AI Agent with CodeEngine, Knowledge Graph, and Kimi-style UI

EggAgent — self-improving AI agent framework (all-in-one)

OpenCode plugin that predicts your next message and shows it as ghost text — role-plays as you using your conversation history. /pred-on to enable.