GITHUB TOPIC
8projects include this topic
The "agent-loop" topic on GitHub groups 8 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by COG-second-brain with 1.2k GitHub stars. COG-second-brain — Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
huytieu
Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
tsrigo
A runnable TypeScript tutorial that builds a minimal DeepSeek-style agent harness from scratch.
euuuuuuzer
A loop dock for DeepSeek Harness: one harness, multiple agent loops.
pzc2004
Moonglow Frostfin — a loop plugin that lets Kimi Code itself directly drive DeepSeek Harness sessions. DSH's shell, Kimi's brain, direct ACP, no middleman. Moonglow Frostfin — Kimi Code itself as the agent loop of DeepSeek Harness. ACP-bridged, no middleman: DSH's shell, Kimi's brain.
FreePeak
Bounded agent loop for DeepSeek Harness: budget ceilings, cheap-first routing, loop hygiene detectors, and a human-in-the-loop ops dashboard.
dancingteeth
Fix-until-green agent loop with shell-verify-as-truth, pluggable multi-runtime workers (Cursor/Cline/OpenCode/Codex/DSH/Pi), and fresh context per iteration.
yunxiyang
Continue a DeepSeek Harness agent turn whose model narrated its next action but called no tool.
sam-midlight
DRAFT — DeepSeek Harness guard that breaks an agent out of a tool-call loop and escalates to a stronger model for one concrete next action. Window-based detection with a progress epoch, so it catches cycles the stock single-slot repeat guard resets away.