#loop-engineering (17 Repositories)
Ranked open-source repositories tagged with #loop-engineering, scored by pull request acceptance likelihood and maintainer engagement velocity.
61.4%
11.7h
17 repositories tagged #loop-engineering
huangruiteng/loopx
Long-horizon agent control plane for durable, governed work across Codex, Claude Code, and other harnesses.
QoderAI/better-harness
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.
rongxinzy/RongxinAI
An all-in-one local AI Agent workspace with a fully self-developed stack
rpamis/comet
Comet: agent skill harness for turning ideas into evaluated workflows
loopx-project/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.
agentscope-ai/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.
diodeme/Gold-Band
Desktop app for harness engineering, loop engineering, graph engineering—and whatever comes next in local AI-agent workflows.
NevaMind-AI/memU
Personal memory across agents
forefy/.context
AI Agent Skills, Loops and Dynamic Workflows for Security Auditing, Pentesting and Research
modiqo/waggle
Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.
YTwsy/OpenSurge-for-Mac
Surge-style whole-home gateway and control plane for macOS with IPv4/IPv6 support— mihomo TUN, dnsmasq-powered DHCP/DNS, per-device routing, and an agent-friendly validation workspace.
Mark393295827/third-brain-v7-skills
agent wiki +engineering skills
gintasz/unigent
Build stateful agent workflows with typed outputs, reusable tools, session forks, and ordinary TypeScript.
romiluz13/cc10x
The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.
agentic-in/inferoa
Inference-native Tokenmaxxing Agent Harness for Loop Engineering
ant-research/AntOmniEvo
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
whut09/opencode-plusplus
OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact analysis, and repair loops.OpenCode++：面向 OpenCode 的 AI 编程可靠性增强框架，为其增加上下文管理、编辑边界、命令证据、验证门禁、影响分析与修复闭环能力。