CodeAlmanac – Self-updating wiki for your coding agent (local, Apache)
Hello good people of HN, This is Rohan from Almanac (YC S26). Today I want to share CodeAlmanac. It is a self-updating wiki for your coding agent. It lives in your repo as Markdown files and updates from your conversations with your agent. It’s open-source, local, and free. How it works 1. Install the CLI and pick your agent (it uses your CC or Codex sub) 2. It scans your codebase and generates an initial wiki. 3. A background job reads your agent conversations every few hours and updates the wiki 4. Your agent queries the wiki through a local SQLite index, using commands like codealmanac…
What it does
In the maker’s words, at launch
Hello good people of HN, This is Rohan from Almanac (YC S26). Today I want to share CodeAlmanac. It is a self-updating wiki for your coding agent. It lives in your repo as Markdown files and updates from your conversations with your agent. It’s open-source, local, and free. How it works 1. Install the CLI and pick your agent (it uses your CC or Codex sub) 2. It scans your codebase and generates an initial wiki. 3. A background job reads your agent conversations every few hours and updates the wiki 4. Your agent queries the wiki through a local SQLite index, using commands like codealmanac search and codealmanac show. Principles it’s based on Conversations as a primary source: There’s a lot you discuss with your agent, and there’s a lot said in those conversations that isn’t directly seen in the code. Why the code is shaped the way it is, what ideas you’ve explicitly rejected, and repeatable procedures that the agent did. We document what’s relevant for future agent runs from there. Maintenance, maintenance, maintenance: An organised wiki is a queryable wiki. Since the first wiki, WikiWikiWeb, people have talked about the need for wiki gardening (see: https://wiki.c2.com/?WikiGardener=). In CodeAlmanac, an agent gardens your wiki every few hours. Docs as code: The wiki lives in your repository as a folder, following the docs as code philosophy See: https://www.writethedocs.org/guide/docs-as-code/ Frequent updates: An outdated wiki is worse than no wiki (see: https://www.trevorlasn.com/blog/outdated-docs-are-tech-debt ). Almanac updates the wiki every 5 hours, and the time between updates is configurable. What goes in the wiki We have borrowed heavily from the Diataxis framework(https://diataxis.fr/). Here’s some of the things the wiki covers: How-to guides (AKA Skills): These cover repeatable procedures and explain things step by step to the agent (eg., How to deploy the CLI, see: https://git.new/2uKhYr7 . They function much the same way as skills, but are connected to the rest of the knowledge base. I talk more about why we think skills are the wrong abstraction here. Decisions: In every conversation with your agent, you make many important decisions. Almanac saves these inside the decisions folder. For example, our pipeline doesn’t commit code directly and instead lets the underlying model do it. This was automatically documented here: https://git.new/6M6Cprw Architecture: Every time you start a new run, your agent needs to read and piece together the codebase. This burns tokens unnecessarily, especially on large codebases. We maintain docs on the entire architecture so it can read only what’s relevant: https://git.new/FJQdHVh. Would love to hear your feedback and any feature requests! Check it out here: https://github.com/AlmanacCode/codealmanac/ (We only support macOS right now, but are working to support Linux/Windows)
Does the same job
all alternatives →
OpenCode SuperappJul 2026 · opencodesuper.app · ▲128The power of Codex with local, self-hosted models and voice
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, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
