#harness

Hermes-style persistent memory and learning loop for Pi coding agent

Meerkat - A modular, high-performance agent harness built in Rust.

Companion products for AI-assisted software work.

Like Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test and measure they actually work. Claude Code + Codex.

Local runtime harness substrate for project-scoped agent sessions.

The official safe, modular native harness for BaseCradle — an AI Research Lab and Modular Agentic Framework where humans and AI are equal peers — same accounts, same permissions, same API. Early development.

A governance harness for AI coding.

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.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

HotPlex — Unified access layer for AI Coding Agent.

A .NET version of test262 ECMAScript test harness

TAP-inspired unit test library for Node, Deno, Bun, and browsers. ES modules, TypeScript, zero dependencies.

Lovable for your terminal: a frontend harness on top of Claude Code, Codex, and 6 other coding agents.

🎸 A project-level orchestrator for AI coding agents — Go & Charm stack implementation of OpenAI's Symphony

Open-source Harness for DeFi Agents on Sail Protocol.

Attention is your scarcest resource. Chief is the local-first layer that guards it — turning every agent, alert, and feed into one honest call: interrupt, or not.

Framework-agnostic agent-harness doctor: deterministic checks for good agent-harness practices

Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

Secure, Modular Postgres for Teams

One CLI across many agentic coding harnesses — run prompts in parallel, get uniform JSON.

kimi k2.7 terminal based coding agent & harness running on your own Cloudflare account.

Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.

An opinionated full-stack agent harness with native memories, long running tasks, and multi-agent relay

Model-agnostic agentic runtime for the terminal — any local model becomes a capable agent. The intelligence lives in the harness, not the weights.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

Опис репозиторію не опубліковано.