# EverMind-AI/Raven

> A Python multi-agent platform that generates DAGs and orchestrates specialized agents (Research, Code, Design, Oncall) for complex tasks, including harness self-improvement.

- Magnitude: 5.9 out of 10 — Breakout
- Stars: 4,672 total · +255 stars today, ≈ 370 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-05-21 · Last push: 2026-09-29
- GitHub: https://github.com/EverMind-AI/Raven · Homepage: https://raven.evermind.ai · Page: https://gitnova.dev/en/r/EverMind-AI/Raven

## Useful for

- Run autonomous deep research with a report and traceable sources
- Assemble a team of agents to implement and test code from requirements
- Set up overnight unattended runs of experiments and optimization

## Why it’s here

- 255 stars so far today, about 370 expected by the end of the day. The usual pace is 15 per day, so that's 24× as much.
- Over the last two days the pace is 14× that of the previous week and a half.
- The spike has held for 3 days in a row — not a one-off blip.
- Hacker News: “Show HN: Raven – The harness of harnesses, built for RSI” — 37 points, 5 h ago.
- About 23 forks a day — people are taking the code.

## Star trust

Star growth looks organic.
- Hardly anyone watches for updates: 3 watchers for 4,672 stars.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 121
- Issues and pull requests: 821
- Watchers: 3
- Average over the last week: 110 per day
- Usual pace: 15 per day
- Stars in the last hour (measured): 47
- Latest release: tech-report-v1 (2026-09-27)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-31 … 2026-09-29: 11, 6, 11, 13, 12, 10, 9, 12, 10, 11, 16, 16, 9, 17, 8, 17, 10, 14, 6, 7, 6, 52, 71, 18, 11, 12, 16, 156, 190, 255

## Hacker News

- Show HN: Raven – The harness of harnesses, built for RSI — 37 points, 32 comments: https://news.ycombinator.com/item?id=49890647

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **paperclipai/paperclip** — 8.4 · Breakout · AI agents · TypeScript · +713 stars today, ≈ 1,302 by evening
   Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage them like employees.
   Full card: https://gitnova.dev/en/r/paperclipai/paperclip.md
2. **NVIDIA/OpenShell** — 7.9 · Breakout · AI agents · Rust · +498 stars today, ≈ 787 by evening
   A safe, private runtime for autonomous AI agents: isolated sandbox containers governed by declarative YAML policies restricting filesystem, network, and process access. Manages credential injection for agents like Claude, Codex, OpenCode,…
   Full card: https://gitnova.dev/en/r/NVIDIA/OpenShell.md
3. **mvschwarz/openrig** — 7.8 · Breakout · AI agents · TypeScript · +260 stars today, ≈ 447 by evening
   OpenRig is a harness orchestrator for AI coding agents: a team of agents (Claude Code and Codex) is defined in YAML and booted with one command, turning scattered terminal sessions into a managed team with a lead agent.
   Full card: https://gitnova.dev/en/r/mvschwarz/openrig.md
4. **vectorize-io/hindsight** — 7.2 · Breakout · AI agents · Python · +763 stars today, ≈ 1,437 by evening
   Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server (Docker, pip, Helm) or…
   Full card: https://gitnova.dev/en/r/vectorize-io/hindsight.md
5. **yetone/magpie** — 6.8 · Breakout · AI agents · Go · +561 stars today, ≈ 808 by evening
   A menu-bar utility for macOS/Linux/Windows that lets you pick the model for each AI agent (Codex, Claude Code, Gemini CLI, etc.) and runs a local gateway translating OpenAI and Anthropic APIs between agents and providers.
   Full card: https://gitnova.dev/en/r/yetone/magpie.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-29 15:26 UTC, updated every 30 minutes.