Castra – Strip orchestration rights from your LLMs
I got tired of AI agents forgetting what they were doing the moment their context window filled. The current industry solution is to write massively bloated agent harnesses full of defensive spaghetti just to stop models from drifting. The problem is treating chat history as project state. A conversation is not a ledger. Castra is a compiled Go binary that strips orchestration rights from the LLM. State lives in an encrypted, local SQLite database (castra.db). The LLM is just a stateless executor — it reads the DB, executes a highly constrained task, and the result is written back subject to…
What it does
In the maker’s words, at launch
I got tired of AI agents forgetting what they were doing the moment their context window filled. The current industry solution is to write massively bloated agent harnesses full of defensive spaghetti just to stop models from drifting. The problem is treating chat history as project state. A conversation is not a ledger. Castra is a compiled Go binary that strips orchestration rights from the LLM. State lives in an encrypted, local SQLite database (castra.db). The LLM is just a stateless executor — it reads the DB, executes a highly constrained task, and the result is written back subject to rigid state-machine rules. What it actually does: - 7-Role RBAC: Hard jurisdictional boundaries (Architect plans, Engineer builds, QA tests). - Dual-Gate Approval: A task cannot reach done without explicit, sequential approval from both a QA agent and a Security agent. No self-approving code. - Cryptographic Audit Chain: Every action is logged into a SHA-256 hash-linked, Ed25519-signed ledger. - Multi-Vendor: Works with Claude, Copilot, Gemini, etc. via a standard AGENTS.md protocol. Anything that supports AGENTS.md and can run terminal commands. Proof of Work: I built this by hand up to v1.3.0. Then, I turned Castra on itself. The agents governed by this exact CLI took over and built the architecture up to v3.1.2—including the cryptographic log chain itself. The proof is in castra-log.jsonl in the repo. If you are running multi-agent workflows and hitting the context amnesia wall, stop trying to prompt-engineer your way out of it. Fix the state machine.
Does the same job
all alternatives →
- PEPlano – Edge and service proxy with orchestration for AI agentsJan 2026 · github.com · ▲8
Hey HN — I’m Adil from Katanemo (with Salman, Shuguang, and Meiyu) We previously shared an early version of this project as ArchGW. Based on customer feedback, the scope expanded from “LLM routing and model access” into something broader: delivery infrastructure for agentic applications. We renamed it to Plano and reworked the architecture accordingly. The problem On-the-ground AI practitioners will tell you that calling an LLM is not the hard part. The really hard part is delivering agentic applications to production quickly and reliably, then iterating without rewriting system code every…
- IBI built a firewall for agents because prompt engineering isn't securityJan 2026 · github.com · ▲7
Hi HN, I’m the creator of Cordum. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern. Most "safety" mechanisms rely on system prompts ("Please don't do X") or flimsy Python logic inside the agent itself. If we treat agents as autonomous employees, giving them root access and hoping they listen to instructions felt insane to me. I wanted a way to enforce hard constraints that the LLM cannot override, no matter how "jailbroken" it gets. So I built Cordum. It’s an open-source…
- CRChainFactory – Run Structured LLM Inference with Easy Parallelism2024 · github.com · ▲8
hi everyone. how does moving llm call prompts and output structure definitions away from code into configuration land sound? would you use something like this if it was stable and well documented enough? please don't hold back the criticism. i appreciate all feedback (constructive & otherwise).
- MAMirror AI – LLM agent that takes action, not just chat2025 · themirrorai.com · ▲5
Hi HN, TL;DR Mirror AI is a cross-platform desktop action oriented LLM. Instead of just replying with text, it can run terminal commands, move files, hit APIs, send email/messages, schedule calendar events, query databases etc. - and chain those steps in one request. Why I built it Chatbots are great for answers but stop at the “OK, now go do it” moment. I was copy-pasting between ChatGPT and my shell/IDE/Gmail far too often, so on red-eye flights I hacked a bridge that lets an LLM execute tasks under a permission layer. Friends asked for it, feature-creep happened, and here…
- CAChunkBack – A Fake LLM API server for testing apps without payingNov 2025 · github.com · ▲6
Hi HN, I've been working with LLMs in production for a while both as a solo dev building apps for clients and working at an AI startup. The one thing that always was a pain was to pay OpenAI/Gemini/Anthropic a few dollars a month just for me to say "test" or have a CI runner validate some UI code. So I built this server called ChunkBack, that mocks the popular llm provider's functionality but allows you to type in a deterministic language: `SAY "cheese"` or `TOOLCALL "tool_name" {} "tool response"` I've had to work in some test environments and give good results for experimenting…
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, 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