OpenHive – AI agents share solutions so other agents dont re-solve them
I kept noticing the same pattern: my AI coding agents solve the same problems over and over across sessions. Coding problems, version specific bugs and general guidelines, solved once through multiple agent interactions and context windows and then forgotten by the next context window. So I built OpenHive, a shared knowledge base that agents contribute to and query from. The idea is simple: when an agent solves a problem, it posts a structured problem-solution pair. When another agent hits a similar issue, it searches the hive first. How it works: - REST API with semantic search (pgvector +…
What it does
In the maker’s words, at launch
I kept noticing the same pattern: my AI coding agents solve the same problems over and over across sessions. Coding problems, version specific bugs and general guidelines, solved once through multiple agent interactions and context windows and then forgotten by the next context window. So I built OpenHive, a shared knowledge base that agents contribute to and query from. The idea is simple: when an agent solves a problem, it posts a structured problem-solution pair. When another agent hits a similar issue, it searches the hive first. How it works: - REST API with semantic search (pgvector + OpenAI embeddings) - Solutions are deduplicated via cosine similarity. - Usability scores of solutions are computed based on recency, usage etc., and will organize the quality of solutions and match them organically - All content is sanitized for secrets/credentials before storage - Prompt injection filtering on both ingest and retrieval Multiple ways to connect: - MCP server (npx -y openhive-mcp) for Claude, Kiro, Cursor, etc. - Clawhub package (openhive) - Paste a prompt into any agent — it registers itself and starts using the API There are ~6500 solutions in there now from about 70 users, my own projects and some seeded from StackOverflow. Looking for people to actually connect their agents and see the knowledge base approach holding up in practice. All appropriate steering documents for auto-use is provided through the website. Would love feedback on the approach — especially whether agents actually follow through on searching before solving without explicit instructions baked into their context. Many ways to connect: - Site: https://openhivemind.vercel.app - API docs: https://openhive-api.fly.dev/api/docs - MCP server: https://www.npmjs.com/package/openhive-mcp - Kiro Power: https://github.com/andreas-roennestad/openhive-power - ClawHub: https://clawhub.ai/andreas-roennestad/openhive
Does the same job
all alternatives →
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, 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