Engrim – A universal, local-first SQLite memory engine for AI CLIs

What it does

The Universal Cross-Model & Cross-Agent Episodic Memory Store. A local-first, project-scoped SQLite memory engine that allows developers to freely switch between models and environments ( Google Antigravity , Claude Code , Cursor MCP , Windsurf ) on the SAME project without losing architectural decisions, user constraints, or project state. "Why pay for 200,000 tokens of forgotten noise on every turn? The models are disposable utilities; your project's decisions are not." As context windows scale to 1M+ tokens, developers face attention dilution : reasoning degrades, cost multiplies with every conversational turn, and clearing context causes total amnesia. Tested across 105 continuous…from github.com

• US
  Using SQL's Turing completeness to build Tetris2024 · github.com · ▲338
• AL
  A local-first memory store for LLM agents (SQLite)Dec 2025 · github.com · ▲48
• 
  MCP Memory – Fast Agent Memory Using Google's OKF and SQLite FTS525d ago · github.com · ▲70

  An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. - fellowgeek/mcp-memory

• FC
  Faster, cheaper Claude Code with local semantic code search via sqliteMar 2026 · ory.com · ▲10
• RA
  Retain – A unified knowledge base for all your AI coding conversationsJan 2026 · github.com · ▲45

  Hey HN! I built Retain as the evolution of claude-reflect (github.com/BayramAnnakov/claude-reflect). The original problem: I use Claude Code/Codex daily for coding, plus claude.ai and ChatGPT occasionally. Every conversation contains decisions, corrections, and patterns I forget existed weeks later. I kept re-explaining the same preferences. claude-reflect was a CLI tool that extracted learnings from Claude Code sessions. Retain takes this further with a native macOS app that: - Aggregates conversations from Claude Code, claude.ai, ChatGPT, and Codex CLI - Instant full-text…

• 
  memories.shFeb 2026 · memories.sh · ▲50

  One layer for memories, skills, and rules across any agent

• 
  I trained a 125M model to autocomplete piano on-device▲598

  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 · 18d ago · simedw.com

• 
  Astute▲585

  Automate your B2B brand going viral, with new media creators

  AI · 19d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 26d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  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 · 28d ago · cactuscompute.com

• 
  Monid▲474

  One wallet, every paid tool your agent needs

  AI · 7d ago · monid.ai

• 
  Clara AI SDR▲460

  Turn website visitors into qualified pipeline

  AI · 20d ago · clarasdr.ai

• 
  Open-Source eInk Bike Computer▲411

  OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.

  Dev tools · 3d ago · opentrailpaper.com

• 
  Nex▲351

  Claude Cowork for high-volume GTM workflows

  Life & fun · 4d ago · nex.ai

• 
  Reflexio▲285

  Behavioral learning that makes AI agents better over time

  AI · 6d ago · reflexio.ai

• OD
  Omi Desktop▲273

  Ask your Mac anything you saw or heard

  Life & fun · 4d ago · api.omi.me

• 
  Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s▲239

  I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next Local models really are the future of computing!

  Life & fun · 6d ago · github.com

• 
  Agentic Video Understanding in Gemini▲237

  Agentic video analysis for faster, smarter Gemini insights

  Life & fun · 5d ago · blog.google