Unify memory across agents and improve context rot, written in Rust
Details
- External ID
- 47644841
- Source
- HN
- Company
- —
- Product
- Unify memory across agents and improve context rot, written in Rust
- Website domain
- github.com
- Launched
- April 5, 2026
- Cohort
- —
- Upvotes
- 5
- Upvotes percentile
- 0.11182519280205655
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I was frustrated that memory is usually tied to a specific tool. They’re useful inside one session but I have to re-explain the same things when I switch tools or sessions. Furthermore, most agents' memory systems just append to a markdown file and dump the whole thing into context. Eventually, it's full of irrelevant information that wastes tokens.So I built this local memory layer that unifies memory across agents. Instead of a flat file, it builds a structured knowledge graph of "memory notes" inspired by the paper "A-MEM: Agentic Memory for LLM Agents" (https://arxiv.org/abs/2502.12110). The graph continuously evolves as more memories are committed, so older context stays organized rather than piling up.It captures conversation turns and exposes an MCP service so any supported agent can query for information relevant to the current context. In practice that means less context rot and better long-term memory recall across all your agents. Right now it supports Claude Code, Codex, Gemini CLI, OpenCode, and OpenClaw.Would love to hear any feedback.
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- memory management for ai agents
- Manually corrected
- False
Could you build this?
Yes A cross-agent memory server in Rust storing facts/summaries in a vector database or SQLite and serving them via MCP or a REST API is well within the scope of modern AI-assisted coding.
Discussion
1 comment analyzed.
Competitors mentioned: screenpipe
Concerns raised: relevance scoring complexity - time decay alone insufficient for mixed critical old and recent noise contexts, imperfect context selection even with Claude reasoning on timestamps
Feature requests: improved relevance scoring beyond time-based decay, better distinction between critical vs. noise contexts in persistent memory
Competitors
Other products that read as similar to this one — 316 launches clear the similarity bar, closest 8 shown.
Attention rank: #276 of 317 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 151 days after the earliest competitor.
- Remembrane · hn · 2026-08-07 · 13 upvotes · similarity 0.59
- Memori · ph · 2026-05-28 · 168 upvotes · similarity 0.58
- ctx · hn · 2026-07-02 · 65 upvotes · similarity 0.57
- YourMemory, agentic memory is a pruning problem, not a hoarding problem · hn · 2026-06-07 · 19 upvotes · similarity 0.56
- TraceMem · hn · 2026-01-12 · 15 upvotes · similarity 0.55
- Context-compact · hn · 2026-03-07 · 6 upvotes · similarity 0.55
- ContextPool · ph · 2026-04-13 · 179 upvotes · similarity 0.53
- CoreMem · hn · 2026-05-22 · 5 upvotes · similarity 0.53
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.