Custos — The bouncer for your AI agents
Stop AI agents from doing things they shouldn't.
What it does
Custos is a safety and control layer for AI agents. It sits between an agent and the tools it uses—like APIs, files, databases, shell commands, and MCP servers—and checks every action before it runs. You define what the agent is allowed to do, Custos blocks anything outside those rules, and every action is recorded in a tamper-evident audit trail. It’s open source, works with Python and TypeScript, and is built for teams running AI agents in real-world environments.
Every tool call your AI agent makes is intercepted, policy-checked, and recorded in a cryptographically signed audit ledger. Before execution. Every time.
Every tool call your agent makes — reading files, hitting APIs, running queries — is intercepted, policy-checked, and recorded in a cryptographically signed audit ledger. Before execution. Every time. Custos is infrastructure, not a SaaS dashboard. Drop it in, define a policy, get audited. Every tool call evaluated before execution against a YAML policy. Deny by default. First match wins. No runtime modification needed. Ed25519-signed, SHA-256 hash-chained JSONL. Any modification to any record — including deletion or reordering — breaks the chain instantly. Python signs. Node verifies. Or vice versa. The ledger format is a formal spec — enforced by a cross-language test on every commit.…from sanjaynandanj.github.io
Does the same job
all alternatives →
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 · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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