npm
chandra447/pi-hermes-memory
Hermes-style persistent memory and learning loop for Pi coding agent
MITSep 5, 2026 · metrics 2.10.0
All tags
Catalogue tag
#harness
Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.
96 records
crates.io · npm
lukacf/meerkat
Meerkat - A modular, high-performance agent harness built in Rust.
Apache-2.0Aug 22, 2026 · metrics 2.10.0
npm
paleo/alignfirst
Companion products for AI-assisted software work.
CC0-1.0Sep 5, 2026 · metrics 2.10.0
npm
zernie/vigiles
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.
MITJul 19, 2026 · metrics 2.10.0
crates.io
OpenCoven/coven
Local runtime harness substrate for project-scoped agent sessions.
MITJul 16, 2026 · metrics 2.10.0
PyPI
basecradle/basecradle-harness
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.
MITSep 5, 2026 · metrics 2.10.0
crates.io
govctl-org/govctl
A governance harness for AI coding.
MITJul 28, 2026 · metrics 2.10.0
crates.io · npm
ratel-ai/ratel
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.
MITJul 20, 2026 · metrics 2.10.0
PyPI
CocoRoF/geny-executor
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.
Apache-2.0Sep 5, 2026 · metrics 2.10.0
Go · npm
hrygo/hotplex-worker
HotPlex — Unified access layer for AI Coding Agent.
Apache-2.0Jul 17, 2026 · metrics 2.10.0
NuGet
lahma/test262-harness-dotnet
A .NET version of test262 ECMAScript test harness
MITJul 23, 2026 · metrics 2.10.0
npm
uhop/tape-six
TAP-inspired unit test library for Node, Deno, Bun, and browsers. ES modules, TypeScript, zero dependencies.
BSD-3-ClauseAug 5, 2026 · metrics 2.10.0
npm
aayambansal/squint
Lovable for your terminal: a frontend harness on top of Claude Code, Codex, and 6 other coding agents.
MITAug 7, 2026 · metrics 2.10.0
Go · npm
junhoyeo/contrabass
🎸 A project-level orchestrator for AI coding agents — Go & Charm stack implementation of OpenAI's Symphony
Apache-2.0Jul 26, 2026 · metrics 2.10.0
npm
sail-money/Sailor
Open-source Harness for DeFi Agents on Sail Protocol.
MITJul 23, 2026 · metrics 2.10.0
PyPI
SmileLikeYe/agent-chief
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.
MITJul 21, 2026 · metrics 2.10.0
npm
abpai/harness-doctor
Framework-agnostic agent-harness doctor: deterministic checks for good agent-harness practices
MITJul 23, 2026 · metrics 2.10.0
PyPI · npm
ccf/agentcairn
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.
Apache-2.0Jul 16, 2026 · metrics 2.10.0
npm
constructive-io/constructive
Secure, Modular Postgres for Teams
MITSep 6, 2026 · metrics 2.10.0
PyPI · crates.io
nickderobertis/oneharness
One CLI across many agentic coding harnesses — run prompts in parallel, get uniform JSON.
MITAug 15, 2026 · metrics 2.10.0
npm
sinameraji/kimiflare
kimi k2.7 terminal based coding agent & harness running on your own Cloudflare account.
MITJul 22, 2026 · metrics 2.10.0
PyPI
Ecro/harness-maker
Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.
MITJul 18, 2026 · metrics 2.10.0
npm
dzhng/duet-agent
An opinionated full-stack agent harness with native memories, long running tasks, and multi-agent relay
Apache-2.0Jul 17, 2026 · metrics 2.10.0
PyPI
hackspaces/blueshark-forge
Model-agnostic agentic runtime for the terminal — any local model becomes a capable agent. The intelligence lives in the harness, not the weights.
MITSep 5, 2026 · metrics 2.10.0
Go · npm
agenvoy/Agenvoy
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.
Apache-2.0Sep 5, 2026 · metrics 2.10.0
Packagist
phalcon/talon
No repository description published.
BSD-3-ClauseJul 15, 2026 · metrics 2.10.0
npm · PyPI · crates.io +1
auron-labs/harness-detect
No repository description published.
MITJul 21, 2026 · metrics 2.10.0
Go
lukaszraczylo/harness-sync
One canonical source of truth for skills, agents, MCP servers, LLM endpoints, and global instructions across every LLM harness on your machine.
MITJul 31, 2026 · metrics 2.10.0
Go · npm
ChaseRensberger/wingman
The open-source client-agnostic agent harness
MITAug 2, 2026 · metrics 2.10.0
crates.io
cptpiepmatz/kitest
🪁 A composable test harness toolkit with room to fly.
MITJul 26, 2026 · metrics 2.10.0