SAPIENS
Breaking the Web3 Audit Bottleneck with Intelligence.
What it does
SAPIENS AI is building Agentic Web3 Audit AI, an autonomous system that collaborates with experts to make Web3 safer. By removing audit bottlenecks, it enables continuous, secure deployment through CI/CD with semantic intelligence and automation.
Does a similar job
all alternatives →
- ALAura – Like robots.txt, but for AI actions2025 · github.com · ▲41
Hi, I've been watching the rise of AI agents with a mix of excitement and dread. We're building incredible tools that can browse the web, but we're forcing them to navigate a world built for human eyes. They scrape screens and parse fragile DOMs. We're trying to tame them to act like humans. I believe this is fundamentally wrong. The goal isn't to make AI operate at a human level, but to unlock its super-human potential. The current path is dangerous. When agents from OpenAI, Google, and others start browsing at scale and speed, concepts like UI/UX will lose meaning for them. The entire…
- DBDeterministic browser control for AI agents (~90% on Mind2Web)Mar 2026 · github.com · ▲12
- MAMeta-agent: self-improving agent harnesses from live tracesApr 2026 · github.com · ▲14
We built meta-agent: an open-source library that automatically and continuously improves agent harnesses from production traces. Point it at an existing agent, a stream of unlabeled production traces, and a small labeled holdout set. An LLM judge scores unlabeled production traces as they stream. A proposer reads failed traces and writes one targeted harness update at a time, such as changes to prompts, hooks, tools, or subagents. The update is kept only if it improves holdout accuracy. On tau-bench v3 airline, meta-agent improved holdout accuracy from 67% to 87%. We open-sourced meta-agent.…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology