hermes-trace (Plugins & Extensions)
21d agoen
Source
hermesatlas.comhermes-trace (Plugins & Extensions)hermesatlas.comHermes Trace is a plugin that provides visibility into agent execution by building structured trace graphs of session activity. It utilizes 18 lifecycle hooks to automatically capture LLM calls, tool usage, subagent spawns, and approval requests. Users can analyze these traces via a dedicated CLI or an in-session slash command to identify bottlenecks and track token usage. The system ensures reliability by wrapping all hooks in error-handling blocks and requires no runtime dependencies beyond th
You might also wanna read
DSpark: A Speculative Decoding Framework Using Semi-Autoregressive Generation and Confidence-Scheduled Verification for LLM Inference Acceleration
DSpark is a speculative decoding framework for Large Language Models (LLMs) that improves inference efficiency by combining semi-autoregress
arxiv.org·12h ago
How novice coders can develop AI programs for military applications
MIT·13h ago
What Changes When Your Software Supply Chain Includes AI Writing Your Code?
BackBox.org·18h ago
AI Agents Explained: The Technology Taking Over 2026
BrightCoding·19h ago
NVIDIA Releases Nemotron-Labs-3-Puzzle-75B-A9B: A Compressed LLM for Efficient Inference
NVIDIA has released Nemotron-Labs-3-Puzzle-75B-A9B, a deployment-optimized large language model derived from Nemotron-3-Super-120B-A12B. The
huggingface.co·19h ago
OmniRoute: Free AI Gateway With 231+ Providers and One Unified Endpoint
pyshine.com·1d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.