Agent Harness Python Packages

openlit

OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.

superqode

The harness interoperability layer for coding agent. Agent to Agent connect over ACP, A2A and UHP

desloppify

Agent harness to make your slop code well-engineered and beautiful.

qwenpaw

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

vaultspec-core

Decision-driven harness for coding agents, and humans.

agent-trajectory

Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)

soothe-cli

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

soothe

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

ait-vcs

AI coding agents should work in attempts, not your working tree

localharness

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harness (detailed event steams, logs, and performance data) or quickly replace closed source one (featuring out of the box plugins for web search, image gen, memory, auto research and more in dev).

loopx

A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.

belay-harness

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

pengy

Local-first AI agent harness with 15 tools desktop QT6 GUI, CLI, and web UI

soothe-daemon

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

agenteng

AgentEng: Agent Engineering HQ - CLI, MCP, A2A and Agent Engineering for AgentEng HQ events

memtomem

Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

agent-harness-aibom

AIBOM generator for AI agent harnesses (Hermes, OpenClaw) - CycloneDX 1.6 output for runtime, model, skill, MCP, hook, and secrets-surface components

omnicoreagent

An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, every run survives a crash without silently redoing anything, every step on the record.

house-party-protocol

A local harness for agent teams on Claude Code and Codex CLI: only what they prove counts as done. Waves and lanes split the work, reviewers from another model family judge it, councils keep the dissent that lost, typed decisions with Jev are measured before they are trusted, and approvals are bound to the bytes they approved. No model calls.

subagent-harness-mcp

MCP gateway for Codex to orchestrate external coding-agent harnesses, with normalized lifecycle, localhost settings UI, and fail-closed no-overage safety.

continuity-plane

Continuity Plane｜面向长期 AI 辅助开发的 provider-neutral 控制面，解决压缩遗忘、重复工作与多 Session 竞态；reliable recovery, bounded context, evidence gates, checkpoints, and safe collaboration.

memtomem-stm

Short-term memory proxy gateway with proactive memory surfacing for AI agents

oara-prometheus

OAra Prometheus — an open-source AI agent daemon that runs on hardware you own.

soothe-sdk

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.