The tool enables users to trigger automated development tasks by tagging @Computer in Slack, allowing teams to monitor and guide the agent before it submits finished code. Distributed under the Apache 2.0 license, the architecture runs within a single virtual machine isolated by rootless Podman and backed by git storage. Its Calvin gateway routes Slack requests to systems like Claude Code, Codex, or OpenCode while utilizing Cloudflare Workers. Benchmark results show the platform completes automated pull requests significantly faster than competing closed-source alternatives.
Key points
Development teams can steer autonomous programming tasks through Slack mentions before th…: Development teams can steer autonomous programming tasks through Slack mentions before the agent submits a pull request.
The platform logged an initial code push in 24 seconds, outperforming the 62-second avera…: The platform logged an initial code push in 24 seconds, outperforming the 62-second average recorded by four competing cloud agents.
Organizations can self-host the software or access a managed cloud offering that permits…: Organizations can self-host the software or access a managed cloud offering that permits users to supply their own model subscriptions.
Sources checked by our analysis pipeline: 1
The open-source Devin alternative: a coding agent your team works with in Slack, on its own computers, in your cloud or ours.
Cloud | Self-hosting | Docs | Website | Benchmark | Community | X
OpenComputer is the open source, self hostable alternative to Devin. Mention @Computer
in a Slack thread with a task, it works on its own computer, you & your team can watch and steer it as it goes, and the result lands as a pull request.
It is open source from the compute layer up, so you can run all of it in your own cloud account, or start on OpenComputer Cloud in two minutes.
We built it to feel as fast as Claude Code on your laptop: in our benchmark it opens PRs 3.3x faster than Devin.
OpenComputer is built to be simple to self-host without giving up scale or security. The whole stack runs on a single VM, which we recommend locking down to outbound-only network access.
The VM runs the gateway, Calvin: a thin bridge that listens for Slack events and starts a…
Designed to operate entirely offline on consumer machines like a MacBook Pro, this open-weights looped transformer uses a Mixture-of-Experts architecture to deliver high-end reasoning within a compact 20GB footprint. By executing its middle layers three times per token, the system outscores sub-100-billion-parameter open-weights alternatives on complex agentic coding tasks without requiring massive hardware. Its release provides developers with deep reasoning capabilities on local hardware alongside dynamic infere…
Bad actors are increasingly attempting to extract advanced frontier model capabilities to create unaligned, guardrail-free systems capable of biological or cyber harm. OpenAI has deployed comprehensive countermeasures across its infrastructure to prevent this unauthorized transfer, emphasizing the protection of underlying reasoning traces. These defenses aim to block malicious developers from weaponizing defensive research and dual-use technological discoveries.
Artificial intelligence company Anthropic appears to have solved the Riemann Hypothesis, resolving what has stood as mathematics' crown jewel since Fermat's Last Theorem was settled in the 1990s. Because countless conjectures were previously proven conditional on this single hypothesis, the machine-generated breakthrough instantly unlocks an immense body of mathematical research. However, the historic breakthrough has sparked bittersweet mourning rather than celebration, as observers view it as a signal that human…