HVTracker — Open
Open trust registry for AI agents
What it does
HVTracker is an open-source AI agent leaderboard and trust registry ranking agents by activity, adoption, transparency, safety, provenance, OSSF Scorecard, signed commits, and evidence.
Does the same job
all alternatives →
- TDTrustGraph – Do More with AI with Less (Open Source AI Infrastructure)2024 · github.com · ▲22
Hi HN, We’re Daniel and Mark, the creators of TrustGraph (https://github.com/trustgraph-ai/trustgraph). TrustGraph is an open source, full end-to-end AI infrastructure that automates knowledge graph building and querying along with modular agent integration. A unique aspect of TrustGraph is that the graph building is a one-time process that builds reusable knowledge cores that can be stored, shared, and reloaded. You can read more about TrustGraph knowledge cores here (https://trustgraph.ai/docs/cores/). Throughout our careers, we’ve been faced…
- ABAI Browser Agent Leaderboard2025 · leaderboard.steel.dev · ▲11
- OSOpen-source AI code review agent that's aware of your entire codebase2025 · docs.sourcebot.dev · ▲5
Hey HN! I'm one of the cofounders of Sourcebot, an open source alternative to Sourcegraph. Sourcebot lets you index thousands of repos across multiple platforms (GitHub, GitLab, Bitbucket), and gives you a powerful interface to search across them. You can learn more in our original HN launch post: https://news.ycombinator.com/item?id=41711032 We just added an AI code review agent that reviews your PRs and automatically detects issues that a human reviewer may have missed. We've been using an AI code review agent for a few weeks now, and it regularly catches issues that we…
- 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 · 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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com