Needs review

11 agents tracked · Open-source-first, with limited public GitHub comparators · Ranked by trust score · Updated 2026-09-10 07:32 UTC

HVTracker independently evaluates 11 needs review using daily signals from GitHub, package registries, and security databases. The category is open-source-first, with a limited set of public GitHub-hosted proprietary or source-available comparators when they are important ecosystem reference points. Each agent is scored on activity, adoption, transparency, safety, and identity. The top-ranked needs review is Eve with a trust score of 65.3/100 (Grade B). Other leading projects include ASM and Obsidian Second Brain.

11
Agents
53
Avg Trust
131.9k
Total Stars
0
Grade A
# Agent Trust Stars Language
1 Eve B Listed The Open Framework for Building Agents 65.3 5.0k TypeScript
2 ASM B Listed The universal skill manager for AI coding agents. 65.1 916 TypeScript
3 Obsidian Second Brain C Listed Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-expla 62.7 4.4k Python
4 Engram C Listed Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, a 61.0 6.5k Go
5 TencentDB Agent Memory C Listed TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusab 60.3 26.3k TypeScript
6 Turbovec C Listed A vector index built on TurboQuant, written in Rust with Python bindings 58.0 16.7k Rust
7 Hivemind C Listed Hivemind turns your traces into reusable skills across agents 56.9 1.6k TypeScript
8 AI Town C Listed A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where A 50.4 10.5k TypeScript
9 HyperAgent D Listed AI Browser Automation 41.1 1.6k TypeScript
10 ClawWork D Listed "ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours" 34.8 8.5k Python
11 Supervision D Listed We write your reusable computer vision tools. 💜 26.1 49.9k Python

Grade = trust band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50 — methodology