#agents

Harness Development Kit

The state layer for LLM agents: durable conversations, agent-curated memory, skills, a shared board and a ledger of who did what — on storage you own.

An open registry for discovering, verifying, and trusting AI agents.

Self-hosted completion gate for coding agents: independent verification before done, durable evidence, CLI and local GUI.

Compose agents into a graph over oneharness/onejudge and merge their outputs into one event stream.

Compose a task DAG over oneagentgraph and onevcs: one merged event stream, a pluggable executor seam.

Stream Claude Code's hidden output (thinking, tool calls, subagents) to a separate terminal in real-time

For docs, visit: https://docs.darwiniantools.com or https://deepwiki.com/remyjkim/darwinian-worker

Lorenz is a control plane for dispatching and managing heterarchical agent systems.

複数エージェントのオーケストレーションを中心に据えた Claude Code フレームワーク。

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

One session that watches your other Claude Code sessions: who is busy, who is waiting on you, what each just said, and how to ask one directly

Run agents you don't babysit, and trust the result. awf runs agentic workflows with independent gates that check every step and resumes after crashes.

No repository description published.

Visual feedback tool for agents

Bonk is a code & docs agent that can build, review and triage for you, built on Cloudflare Workers & OpenCode.

Unified control plane and operations console for agent inventory, capability discovery, fleet status, and governance.

TypeScript SDK for x402 buyers and sellers, with bounded Solana Tabs and one-shot multichain payments.

CLI for Goodeye: turn business outcomes into verified AI workflows that agents run reliably.

Installable AI governance harness for Codex, Cursor, Claude, Gemini, Copilot, Engram, and Graphify.

Spec-driven development engine for AI-built software — validated L0–L5 spec trees, an architecture conformance gate, derived AI agent topology & skills, MCP authoring tools, interactive architecture/ERD canvas, and injectable profile/rule packs.

A framework for creating useful AI agents using JavaScript

A skill system for Laravel AI SDK agents. Define reusable AI capabilities with SKILL.md files.

Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.

GRASP — Code architecture visualizer + 150-tool MCP server. Dependency graphs, security scanning, multimodal knowledge graph, ORM tracking, git change impact, graph schema v3. Works with GitHub, GitLab & local dirs. 35 languages. Zero data collection.

Markdown-defined provider-backed agents and deterministic workflows for ACP runtimes.

No repository description published.

An agentic coding assistant written in Golang primarily for use with Golang codebases

NOUS (Νοῦς) — monitor, not a guard. NOUS proves the rules you declare hold across every path your AI agents could take — and anyone can check the proof offline, without trusting the vendor. Not even NOUS. EU AI Act Annex IV.

Eliminate friction for deploying new features. Creates isolated git worktrees, allocates conflict-free runtime values, runs project-defined setup and teardown commands, and launches agents.