docs-cli - coding-agent project state in Markdown
Hi HN I recently published docs-cli to pypi. I created this tool because I noticed that my docs kept getting out of sync: I've been using markdown to track the project's implementation and progress, and it became really hard to keep track of everything. This is a simple tool for your agents to ensure that links and indexes are kept fresh. I included the agent-playbook-suite marketplace since this is how I use it. The docs repo was actually built also using it, so dogfooding since day one :) The Agent Playbook Suite includes everything needed to create a project from start to finish. Linked…
docs-cli - coding-agent project state in Markdown launched on May 25, 2026 with 6 votes, #1,742 of 20,539 launches that month and more than 75% of that year's launches.
What it does
A file-backed workflow for resumable agent-led software projects.
One Claude Code session decides the API. The next writes tests against a different shape. A week later, a fresh agent reads the inconsistent repository and asks you a question you already answered. The hard part of a long agent-led project is not code generation. It is continuity. Agent Playbook Suite is one plugin for Claude Code and Codex that gives the agent a repeatable delivery process. docs-cli is the small Python CLI underneath it. Together they keep decisions, plans, progress, and open questions on disk instead of leaving project state in chat. This post shows how the workflow fits together, what it costs, and where it earns that cost. python3 -m pip install --upgrade docs-cli…from artrichards.github.io
In the maker’s words, at launch
Hi HN I recently published docs-cli to pypi. I created this tool because I noticed that my docs kept getting out of sync: I've been using markdown to track the project's implementation and progress, and it became really hard to keep track of everything. This is a simple tool for your agents to ensure that links and…
Does a similar job
all alternatives →
Project management system for Claude Code2025 · github.com · ▲175I built a lightweight project management workflow to keep AI-driven development organized. The problem was that context kept disappearing between tasks. With multiple Claude agents running in parallel, I’d lose track of specs, dependencies, and history. External PM tools didn’t help because syncing them with repos always created friction. The solution was to treat GitHub Issues as the database. The "system" is ~50 bash scripts and markdown configs that: - Brainstorm with you to create a markdown PRD, spins up an epic, and decomposes it into tasks and syncs them with GitHub issues - Track…
DocsAlot CLIAug 2026 · docs.docsalot.dev · ▲196Let Claude or Codex create and maintain good looking docs
Slack CLI for AgentsFeb 2026 · github.com · ▲99Our team lives in Slack, but we don’t have access to the Slack MCP and couldn’t find anything out there that worked for us, so we coded our own agent-slack CLI * Can paste in Slack URLs * Token efficient * Zero-config (auto auth if you use Slack Desktop) Auto downloads files/snippets. Also can read Slack canvases as markdown! MIT License
TaskShellApr 2026 · taskshell.app · ▲86I initially built this for myself but some folks asked me to open access to it. Let me explain what I built and why. I'm a product designer who transitioned from only designing to building complete software products myself and I found myself using AI coding agents literally every day. I started with cursor, then codex and claude code, then kilo code, and then moved to opencode. The only thing AI agents couldn't get done for me was to keep track of my todos and tasks for all my projects. I ended up vibe coding a todo app separately or using apps like TickTick. The main issue with separate…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 19d ago · stillwet.art
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
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
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com