Harness Hub
All startups

PrimeIntellect

Decentralized AI lab — Prime Agent, the self-improving RLM agent.

PrimeIntellect, the lab known for decentralized training and the INTELLECT model series, open-sourced Prime Agent: a recursive-language-model agent for coding and long-running autonomous tasks whose harness famously took Opus 5 from ~30% to 95.5% on ARC-AGI-3 — evidence that the harness can matter more than the model.

People

Open roles (38)

All 38 roles

Their open-source work

PrimeIntellect-ai/prime-agent

A self-improving RLM agent for coding and long-horizon autonomy.

Maintained by PrimeIntellect

v0.10.5released

Activity

Last push
· yesterday
Latest release
v0.10.5
· 3d ago
Last 90 days
19 releases
  1. v0.10.5

    · 3d ago
  2. v0.10.4

    · 4d ago
  3. v0.10.3

    · 9d ago
  4. v0.10.2

    · 3w ago
  5. v0.10.1

    · 4w ago

Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.

On X

Posts by the company and its team, shown as plain text; “Load on X” loads X's script for that post, which may set cookies.

Follow @PrimeIntellect on X · The X feed

In the news

PrimeIntellect open-sources Prime Agent, a recursive-language-model agent whose harness runs sub-agents as function calls inside a persistent IPython REPL. The launch post reports its harness taking Opus 5 from ~30% to 95.5% on ARC-AGI-3 — the sharpest evidence yet that harness engineering can beat model selection.

In research (1)

Featured

Devin, the AI software engineer, and the Windsurf IDE.

Cognition builds Devin, an autonomous AI software engineer that plans and executes engineering tasks end-to-end, and acquired the Windsurf agentic IDE in 2025. One of the defining startups of the coding-agent wave.

~$10.2B valuation (Sep 2025)

3 pros · 4 cons

Serverless cloud built for AI and agentic compute.

Modal lets teams run inference, fine-tuning and arbitrary agent workloads as serverless Python without managing infrastructure — a common substrate for harness backends at scale.

4 pros · 4 cons

Durable execution for long-running agent workflows.

Temporal's durable execution engine is widely adopted to make agent pipelines reliable: state survives crashes, retries are automatic, and workflows run for minutes or months. A key piece of serious harness infrastructure.

$430M total · $300M Series D (Feb 2026) at $5B valuation

3 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Maintains · 1

Similar entries · 1

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.