luoyuctl/agenttrace
Local-first TUI for AI coding-agent session history: trace cost, tokens, time, tool failures, latency, health, diffs, reports, and CI gates across local agent logs.
The linter for your agent harness. Works with Claude Code, Codex, and Cursor.
Local-first TUI for AI coding-agent session history: trace cost, tokens, time, tool failures, latency, health, diffs, reports, and CI gates across local agent logs.
Claude Code plugin — AI-powered autopilot for managing open source contributions. Track PRs, respond to maintainers, discover issues, maintain velocity.
🛩️ Git-native workflow control for coding agents: approved plans, verification, and reviewable evidence for Claude Code, Codex, Cursor, and Aider.
Turn ad-hoc Claude Code / Codex / Cursor sessions into a repeatable loop — research → plan → wave-execute → close. Parallel sub-agents, inter-wave quality gates, dual GitHub+GitLab integration, F2 Memory + Persona-Panel + gsd-Pattern Adoption. 37 skills · 18 commands · 13 agents · 7360 tests.
agx: Run AI coding agents as a persistent team with objectives, memory, and coordinated work. The same agents built this tool — 167+ merged PRs, 93% clean.
A framework-agnostic, git-native standard for defining AI agents
2 captures since 2026-05-23
AI agent config detected
Key config paths
.github/copilot-instructions.md
CLAUDE.md
templates/configs/templates/CLAUDE.md
tests/fixtures/deep/contradiction/CLAUDE.md
tests/fixtures/deep/large/CLAUDE.md
tests/fixtures/deep/medium/CLAUDE.md
1 more config path detected.
.github/copilot-instructions.md
CLAUDE.md
templates/configs/templates/CLAUDE.md
tests/fixtures/deep/contradiction/CLAUDE.md
tests/fixtures/deep/large/CLAUDE.md
tests/fixtures/deep/medium/CLAUDE.md
tests/fixtures/deep/small/CLAUDE.md