Recursive-Mode for Coding Agents
recursive-mode is an installable skill package for coding agents. It gives your agent a file-backed workflow for requirements, planning, implementation, testing, review, closeout, and memory, instead of leaving the whole process scattered in context. Long-running agent work has a common failure mode: requirements, decisions, and plans live in the conversation. Once the session ends or the context window overflows, the agent loses track of what was decided, what was implemented, and why. recursive-mode solves context rot by making repository documents the source of truth for every phase.…
What it does
In the maker’s words, at launch
recursive-mode is an installable skill package for coding agents. It gives your agent a file-backed workflow for requirements, planning, implementation, testing, review, closeout, and memory, instead of leaving the whole process scattered in context. Long-running agent work has a common failure mode: requirements, decisions, and plans live in the conversation. Once the session ends or the context window overflows, the agent loses track of what was decided, what was implemented, and why. recursive-mode solves context rot by making repository documents the source of truth for every phase. Requirements, plans, evidence, state, and decisions live in files that persist across sessions, contributors, and repositories. Prompts become short commands, not full specs. The workflow is built on a few simple rules. Each development phase produces one locked output document. Each phase uses earlier phase outputs as input. Before the agent can exit a phase and move forward, it must satisfy defined criteria based on the workflow and prior docs. It is called recursive-mode because the workflow keeps revisiting its own outputs. Later phases consume earlier artifacts. Audited phases loop through draft, audit, repair, and re-audit until the work is actually ready. Closeout feeds validated lessons back into decisions, state. The generated docs are both human-readable and machine-readable. They give strong traceability for what was built, why it was built that way, what changed, and how it was validated. Instead of reconstructing rationale from chat logs, you can point directly to the repo artifacts. That also makes recursive-mode useful beyond day-to-day development. The run docs, together with code diffs in the worktrees, form a high-quality dataset for fine-tuning, auto-training, or self-distillation against your own codebase and engineering process. Chat is treated more like a CLI. You use it for commands, not as the place where critical project knowledge lives. You can refine a plan with the agent, ask it to turn that plan into a new recursive run, or create the run folder and requirements doc yourself, and tell the agent to "implement run 01" to start the run. recursive-mode is a free open source alternative to Missions. It is for developers and teams who want auditable agent runs, recorded evidence, and long or resumable work that can continue without losing context. Installation: npx skills add try-works/recursive-mode --skill '*' --full-depth skills.sh: https://skills.sh/try-works/recursive-mode/recursive-mode GitHub: https://github.com/try-works/recursive-mode For detailed documentation: https://recursive-mode.dev/ Write-up with benchmark: https://try.works/recursive-mode-for-coding-agents
Does the same job
all alternatives →
Deep Work PlanJun 2026 · deepworkplan.com · ▲114Models matter. Context matters more. Give your agent a plan.
- 2C20+ Claude Code agents coordinating on real work (open source)Feb 2026 · github.com · ▲53
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
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 · 27d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app