AMP
open-source memory server for AI agents (MCP, SQLite, D3.js)
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hi HN,I’m Akshay. I built AMP because I was tired of my AI agents having "amnesia" the moment I closed the terminal.Like many of you, I use Claude/Cursor daily. RAG is great for searching documentation, but it’s terrible for continuity. It chunks text blindly, losing the narrative. When I asked my agent "Why did we decide to use FastAPI last week?", it would hallucinate or just give me generic pros/cons because the specific context of our decision was lost in a vector soup.So I decided to build a proper *Hippocampus* for my agents.*What is it?* AMP is a local-first memory server that sits between your agent and its LLM. It implements a "3-Layer Brain": 1. *STM*: A scratchpad for what we are doing right now. 2. *LTM*: Consolidated facts and insights (promoted from STM). 3. *Galaxy Graph*: A force-directed knowledge graph (d3.js) that physically links related concepts.*The Tech Stack* * *Protocol*: Built natively for the *Model Context Protocol (MCP)*. If you use Claude Desktop or Cursor, it works out of the box. * *Backend*: Python, FastAPI, SQLite (no docker needed). * *Search*: Hybrid (Keyword + Vector) using FastEmbed. * *Viz*: A 60fps local dashboard to actually see your agent's brain growing.*Benchmarks* I didn't want just another vector wrapper, so I focused heavily on retention. I benchmarked it against Mem0 (a popular alternative) on the LoCoMo dataset. * *AMP*: 81.6% Recall (Context-First) * *Mem0*: 21.7% Recall (Extraction-First)It turns out that preserving the narrative (who/what/when) before summarizing is key to avoiding "I don't know" answers.I’d love to hear your thoughts on the architecture. Does your agent need a hippocampus?Repo: https://github.com/akshayaggarwal99/amp
HN · launched Dec 14, 2025 · 5 upvotes (top 90%) · 0 views
Niche: ai agent memory infrastructure · 351 launches, 8 in the last 7 days ▼ -70% · Explore this niche →
Category and tags
- Horizontal
- Data infrastructure
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 351 launches in ai agent memory infrastructure →
Could you build this?
Yes It is an MCP server paired with SQLite storage and a D3.js visualization dashboard to store and retrieve agent conversation history.
Discussion
1 comment analyzed.
Concerns raised: Unwanted memories from old conversations bleeding into new ones, Memory fragments causing off-topic distractions
Feature requests: Better control over which memories persist across conversations, Ability to compartmentalize or filter memories by context
Competitors
Other products that read as similar to this one : 371 launches clear the similarity bar, closest 8 shown.
Attention rank: #356 of 372 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 40 days after the earliest competitor.
- Mwe-MCP · hn · 2026-07-23 · 5 upvotes · similarity 0.51
- Slowave · hn · 2026-09-14 · 5 upvotes · similarity 0.48
- ClawMem · hn · 2026-03-22 · 5 upvotes · similarity 0.47
- Model-agnostic cognitive architecture for LLMs · hn · 2025-11-18 · 6 upvotes · similarity 0.46
- YourMemory, agentic memory is a pruning problem, not a hoarding problem · hn · 2026-06-07 · 19 upvotes · similarity 0.46
- hx-stomp-nam · github · 2026-10-10 · 14 upvotes · similarity 0.46
- memory-brain · github · 2026-10-28 · 81 upvotes · similarity 0.45
- Memori · ph · 2026-05-28 · 168 upvotes · similarity 0.45
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.