K9 Audit – Causal intent-execution audit trail for AI agents
On March 4, 2026, my Claude Code agent wrote a staging URL into a production config file — three times, 41 minutes apart. Syntax was valid, no error thrown. My logs showed every action. All green. The problem was invisible because nothing had recorded what the agent intended to do before it acted — only what it actually did. K9 Audit fixes this with a causal five-tuple per agent step: - X_t: context (who acted, under what conditions) - U_t: action (what was executed) - Y*_t: intent contract (what it was supposed to do) - Y_t+1: actual outcome - R_t+1: deviation score (deterministic — no LLM,…
What it does
In the maker’s words, at launch
On March 4, 2026, my Claude Code agent wrote a staging URL into a production config file — three times, 41 minutes apart. Syntax was valid, no error thrown. My logs showed every action. All green. The problem was invisible because nothing had recorded what the agent intended to do before it acted — only what it actually did. K9 Audit fixes this with a causal five-tuple per agent step: - X_t: context (who acted, under what conditions) - U_t: action (what was executed) - Y*_t: intent contract (what it was supposed to do) - Y_t+1: actual outcome - R_t+1: deviation score (deterministic — no LLM, no tokens) Records are SHA256 hash-chained. Tamper-evident. When something goes wrong, `k9log trace --last` gives root cause in under a second. Works with Claude Code (zero-config hook), LangChain, AutoGen, CrewAI, or any Python agent via one decorator. pip install k9audit-hook
Does the same job
all alternatives →
- SRShikigami, run AI coding agents in parallel, each in a Git worktreeJul 2026 · shikigami.dev · ▲7
Hello all, I'm a software developer. Over the last few months more and more of my work has turned into using coding agents instead of typing the whole code myself. Usually a few claude sessions at once, sometimes codex, one per feature or per revealed bug. I ran them in a split terminal for a few weeks, and quickly spotted two main problems. The first is that I couldn't easily tell which agent was stuck waiting on me and which was still working, so I'd cycle through sessions and checking on them. The second one: agents sharing a single branch step on each other. Two of them could be editing…
- CSCase study: A coding agent refactors a 750k LOC app, no code reviewJul 2026 · ▲6
In the following case study, the AI coding agent rebuilds a core system invariant in just three days, with minimal human input, running 31 verification passes and correcting 201 errors, before shipping code with zero bugs, zero regressions, and zero technical debt. https://aisovereignlabs.ai/docs/case-study/liveSession/case-... Disclaimers: This case study is NOT: - a project written from scratch - yet another Rust transpilation - a clone of an open-source project found in the LLM's training data - a Super Mario clone in HTML It IS: - a complex application…
- AFAgent Flow: A beautiful way to visualize Claude Code actionsMar 2026 · github.com · ▲5
Hey HN, Claude Code is powerful, but its execution is a black box. You see the final result, not the journey. Agent Flow makes the invisible visible in realtime: - Understand agent behavior: See how Claude breaks down problems, which tools it reaches for, and how subagents coordinate - Debug tool call chains: When something goes wrong, trace the exact sequence of decisions and tool calls that led there - See where time is spent: Identify slow tool calls, unnecessary branching, or redundant work at a glance - Learn by watching: Build intuition for how to write better prompts by observing how…
- IBI built new type of dev environment for agentic coding2025 · github.com · ▲6
The main goal of this was to be able to not just run multiple Claude Code sessions at once, but actually manage them and keep track of what I was doing. Sometimes this is multiple attempts on the same task, sometimes I work several tasks at once. Really I was just sick of twiddling my thumbs waiting for the coding agent to finish, and I wanted it to be easy to work on/review/test another change while I waited.
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
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
