Ouijit, an open-source task and terminal manager for coding agents
Hi HN, I’m working on Ouijit. It’s a project and task-based terminal session manager that provides a few basic but useful tools for agent workflows: - Terminal sessions in Ouijit have access to the ouijit CLI, and supported agents (Claude, Codex, Pi) can work with it out of the box to manage tasks and customize a personal development workflow - Tasks live on a kanban board that supports hooks for task lifecycle events (eg. ‘Run this script when a task moves to ‘in progress’) I’ve found this simple combination to be very expressive and flexible for adapting to changing workflows. I made the…
In plain words
Ouijit is an open-source terminal session manager designed for coding agents and developers. It organizes work through a kanban board interface where tasks can trigger automated actions during their lifecycle. Terminal sessions integrate with the Ouijit CLI and support AI agents like Claude, Codex, and Pi, enabling them to manage tasks and workflows directly. The tool includes features like task isolation using Git worktrees and agent status tracking, aimed at helping developers and agents coordinate complex coding projects efficiently.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I’m working on Ouijit. It’s a project and task-based terminal session manager that provides a few basic but useful tools for agent workflows: - Terminal sessions in Ouijit have access to the ouijit CLI, and supported agents (Claude, Codex, Pi) can work with it out of the box to manage tasks and customize a personal development workflow - Tasks live on a kanban board that supports hooks for task lifecycle events (eg. ‘Run this script when a task moves to ‘in progress’) I’ve found this simple combination to be very expressive and flexible for adapting to changing workflows. I made the V1 a couple months ago for fun, and have kept at it since a friend shared they had logged an 8 hour work session in it. Along the way I’ve baked in lots of what I believe are table-stakes for this type of tool, like task isolation via Git worktrees, agent working/idle status with sound and notifications, diff/markdown plan/URL previews, and support for VM sandboxing using Lima. It’s free and open source with no login or telemetry, so feedback is highly appreciated. Github: https://github.com/ouijit/ouijit Website: https://ouijit.com
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com