AgentDbg
Debug everything your AI Agent does, locally
What it does
Record agent runs to local JSONL and inspect a timeline of LLM calls, tool calls, state, and errors. Includes loop warnings. No cloud, no accounts, no telemetry. 1. Timeline UI for LLM/tool calls/errors/state 2. Loop warnings for repetitive behavior 3. Redaction on by default + truncation limits 4. Works with any Python; optional LangChain/LangGraph handler 5. Export runs to a single JSON
Does the same job
all alternatives →- AJAgents.json – OpenAPI Specification for LLMs2025 · github.com · ▲212
Hey HN, we’re building an open specification that lets agents discover and invoke APIs with natural language, built on the OpenAPI standard. agents.json clearly defines the contract between LLMs and API as a standard that's open, observable, and replicable. Here’s a walkthrough of how it works: https://youtu.be/kby2Wdt2Dtk?si=59xGCDy48Zzwr7ND. There’s 2 parts to this: 1. An agents.json file describes how to link API calls together into outcome-based tools for LLMs. This file sits alongside an OpenAPI file. 2. The agents.json SDK loads agents.json files as tools for an LLM that…
- ARAgentflow – Run Complex LLM Workflows from Simple JSON2023 · github.com · ▲51
So, it feels like this should exist. But I couldn't find it. So I tried to build it. Agentflow lets you run complex LLM workflows from a simple JSON file. This can be as little as a list of tasks. Tasks can include variables, so you can reuse workflows for different outputs by providing different variable values. They can also include custom functions, so you can go beyond text generation to do anything you want to write a function for. Someone might say: "Why not just use ChatGPT?" Among other reasons, I'd say that you can't template a workflow with ChatGPT, trigger it with different…
- RTReal-time dashboard for Claude Code agent teamsApr 2026 · github.com · ▲77
This project (Agents Observe) started as an exploration into building automation harnesses around claude code. I needed a way to see exactly what teams of agents were doing in realtime and to filter and search their output. A few interesting learnings from building and using this: - Claude code hooks are blocking - performance degrades rapidly if you have a lot of plugins that use hooks - Hooks provide a lot more useful info than OTEL data - Claude's jsonl files provide the full picture - Lifecycle management of MCP processes started by plugins is a bit kludgy at best The biggest takeaway is…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
