MCP Memory Gateway
Thumbs down a mistake. Your AI agent never repeats it.
What it does
ThumbGate is the safety net for AI coding agents. Give a thumbs-down to a bad action once, and your agent will never ship that mistake again. Every downvote becomes a concrete prevention rule and a pre-action gate that blocks known-bad actions before they execute across 36 tools (git, shells, files, HTTP, clouds). v0.8.4 ships improved rule validation, faster gate checks, and a live dashboard. Unlike Mem0 (memory) or SpecLock (specs), ThumbGate enforces lessons at the moment of action.
Does a similar job
all alternatives →
MCP Memory – Fast Agent Memory Using Google's OKF and SQLite FTS524d ago · github.com · ▲70An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. - fellowgeek/mcp-memory
Cortex by SKYNETLAB14d ago · skynetlab-cortex.com · ▲85The memory layer that decides what's worth remembering
Noisegate – a differential-privacy gateway for untrusted AI agentsJul 2026 · github.com · ▲19Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable att
- OSOpen-Source Gateway to Stop Tool-Abusing Prompt InjectionsOct 2025 · archestra.ai · ▲9
Hi HN, Matvey, Ildar, Joey, and Dominik here. If you're building LLM agents that use tools, you're probably worried about prompt injection attacks that can hijack those tools. We were too, and found that solutions like prompt-based filtering or secondary "guard" LLMs can be unreliable. Our thesis is that agent security should be handled at the network level between the agent and the LLM, just like a traditional web application firewall. So we built Archestra Platform: an open-source gateway that acts as a secure proxy for your AI agents. It's designed to be a deterministic firewall against…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
