StartupEst. 2026 · Early
EverMind AI
Raven — the harness of harnesses, built for recursive self-improvement.
EverMind AI builds Raven, an open-source, trusted, persistent and self-evolving multi-agent ecosystem designed for recursive self-improvement (RSI), alongside memory-sparse-attention research for scaling end-to-end memory to 100M tokens.
People
Co-founder & CEO
Context engineering & memory
Their open-source work
Python · ≈6.3k stars · Apache-2.0
EverMind-AI/Raven
The harness of harnesses, built for RSI.
Maintained by EverMind AI
v0.2.8releasedActivity
- Last push
- · yesterday
- Latest release
- v0.2.8
· 4d ago - Last 90 days
- 11 releases
v0.2.8Raven 0.2.8 (2026-11-17)
· 4d agoRaven 0.2.8 is a patch release. It brings OpenShell sandboxing and network permissions, DAG replanning that carries unfinished work forward, task delegation as the host's default, a context-window breakdown with better prompt-cache reuse, and more reliable Task Board updates…
v0.2.7Raven 0.2.7 (2026-11-03)
· 2w agoRaven 0.2.7 is a patch release. Each conversation now keeps a Task Board of the matters it is pushing, with a Task Board page across conversations; the trajectory page is redrawn as an agent waterfall that shows an external agent's own steps and can replay a session from its…
v0.2.6Raven 0.2.6 (2026-10-27)
· 3w agoRaven 0.2.6 is a patch release. This release changes how a long conversation stays inside the model's context window: the new compacting history strategy is the default, and the previous Curator is one setting away. It also reads portable Agent Plugins packages, strengthens…
v0.2.5Raven 0.2.5 (2026-10-20)
· 4w agoRaven 0.2.5 is a patch release. This release strengthens multi-agent coding, adds remote agent execution on registered machines, introduces conditional branches in DAG workflows, and improves native Windows support. Raven can delegate tasks to connected agents on any registered…
v0.2.4Raven 0.2.4 (2026-10-03)
· 7w agoRaven 0.2.4 is a patch release. Raven can now read and change its own configuration from the conversation: a new raven_config tool reads any setting without asking, asks before every write, and never takes a key through the chat (#833). Four things behave differently once you…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
On X
No posts from them in our X feed yet.
In the news
Open Source · Hacker News · Sep 29, 2026
EverMind AI releases Raven, a trusted, persistent, self-evolving multi-agent ecosystem built for recursive self-improvement — agents that modify their own harness under governance. The Show HN thread became a running debate on how much autonomy a harness should hand an agent over itself.
Neighbours in the directory
San Francisco, CA · Est. 2022
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
~$75M raised
San Francisco, CA · Est. 2023
Conversational AI agents for customer experience.
Sierra, co-founded by Bret Taylor and Clay Bavor, builds production conversational agents that resolve real customer issues with guardrails, evaluation and human escalation — a template for deploying vertical agents at the enterprise edge.
~$10B valuation (Oct 2025)
Coral Gables, FL · Est. 2023
Multi-agent orchestration, from open-source framework to enterprise platform.
CrewAI popularized role-based multi-agent teams ('crews') with a simple mental model and ships an enterprise control plane for deploying, monitoring and governing them.
$18M Series A led by Craft Ventures (2024)
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Similar entries · 1
- RavenProject
Mentioned in · 1
- Show HN: Raven – The harness of harnesses, built for RSINews · 2026-09-29