Compétence d'observabilité IA pour Claude Code permettant de déboguer les agents LangChain/LangGraph en récupérant les traces d'exécution depuis LangSmith Studio.
Source
GitHub
Dernière activité
6 avr. 2026
Étoiles28Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.
Source
GitHub
Langage
Python
Dernière activité
15 oct. 2026
Étoiles24Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude Code skill + Python CLI. MIT.
Source
GitHub
Langage
Python
Dernière activité
13 sept. 2026
Étoiles24Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative
CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+
Source
GitHub
Langage
Python
Dernière activité
20 oct. 2026
Étoiles23Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · -4,17% d’évolution relative
Watch your Claude Code subagents work as a pixel-art office. Rewind any second, see what every agent cost, and turn any session into a timelapse GIF. Read-only, 100% local.
Source
GitHub
Langage
TypeScript
Dernière activité
27 sept. 2026
Étoiles22Mesuré · 21 oct. 2026
Momentum07 jours · Mesuré · 0% d’évolution relative