Octomind open-sources CLI coding agent runtime
Understand this story
Octomind has open-sourced a CLI coding agent runtime that uses MCP tools to let models read and write files, execute shell commands, and schedule sub-agents; the same session engine supports five run modes: interactive, pipeline, daemon, WebSocket, and ACP sub-agent. In terms of usage, Octomind says the fastest path is Octomind Cloud, which comes with models and requires no configuration; to use your own model provider key, you can skip login and export the key. The first time a given specialist runs, it may install tools and ask for credentials. On usage limits, a single request that exceeds the threshold will stop; when a session reaches the threshold, the terminal session asks y/N whether to continue, while a non-interactive octomind run stops with exit code 75.
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIOctomind – open-source AI harness that saves your tokens, static rust
Octomind is a CLI-first AI coding agent runtime distributed as a single Rust binary that gives an LLM repo access through MCP tools, running interactively, piped, as a daemon, over WebSocket, or as an ACP sub-agent. It enforces guardrails as TOML policy, supports per-role models and spend thresholds, and reports solving 24 of 25 held-out tasks on its octobench benchmark at $63.43 versus 23/25 at $81.79 for claude code + claude-opus-5. It installs via script, Homebrew, Scoop, Cargo, or Docker and is licensed Apache 2.0.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 4 00:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.