Octomind solves 24 of 25 real PR tasks at half the cost of opencode on the same model
Octomind – open-source AI harness that saves your tokens, static rust
Octomind is an open-source, CLI-first AI coding agent runtime written in Rust: one binary, any model, MCP-native, and runnable interactively, piped through stdin, as a daemon, over WebSocket, or as an ACP sub-agent. On octobench's 25 tasks harvested from merged pull requests, it solved 24 with glm-5.2 for $63.43 and 3.6 hours — beating opencode on the same model, which solved 19 at roughly double the cost. Guardrails are policy-as-code in TOML, and adaptive compression keeps long sessions sharp.
The harness matters. opencode used the same model and endpoint; octomind solved 24 vs 19 at roughly half the cost.
- Murfalo
Holy tagline. "The CLI-first AI coding agent runtime. Pipe it, schedule it, embed it. One binary, any model, MCP-native — built for autonomous work, not just chat."
I feel like I'm taking crazy pills...
- closetheloopdev
I'm not sure if I missed something, but the benchmarks [0] look outdated since they use Claude Opus 5 (instead of Opus 5.5), GPT 5.6 Sol (instead of 6.1 Sol), and GLM 5.2 (instead of DeepSeek V4.1 Flash 1017, which is the most popular model on OpenRouter currently [1]). I also cannot find any information regarding thinking efforts for each.
Since these benchmarks were done in July, they were probably using older versions of Claude Code, Codex, and OpenCode as well.
Would appreciate if the benchmarks are updated, and the thinking efforts and the versions of Claude Code, Codex, and OpenCode are specified.
- jszymborski
I'd like to see this benched against oh-my-pi because I've really been digging how it does compaction / snapshotting.
- buster
Why would i choose that over maki.sh? A comparison to maki would be great!
- sharathr
have you taken a look at Codeoid: https://github.com/highflame-ai/codeoid, we use it regularly across everyone in our team and its really great.
Especially the ability to switch an ongoing conversation from Claude Code to Codex or Gemini (if you run out of tokens).