AI/ML●●●Banger
Agent Memory DB – Episodic memory for agents (97.5% vs. 85% recall)
Vector memory for agents beats truncation; Rust core with Python/Node/Go bindings.
Solve My ProblemBig BrainShip It
andy9829
204mo ago
Back to browse
Rememori zero-dependency agent memory that runs anywhere JS runs
by GiorgioDotcom·Jul 7, 2026·1 point·0 comments
AI Analysis
●●●BangerBig BrainZero to OneCozy
Entity-graph recall bonus surfaces memories when words don't match but entities do.
Strengths
- •Zero dependencies, ~8 kB core, pure TypeScript runs anywhere JS runs.
- •Entity-based graph bonus on cosine similarity finds connections plain vector search misses.
- •MCP server integration gives Claude Code persistent memory with one command.
Weaknesses
- •Agent memory category has LangChain, LlamaIndex, Mem0 already competing.
- •Entity extraction heuristic is pluggable but built-in version is basic.
Category
Target Audience
AI agent developers needing persistent memory
Similar To
LangChain Memory · LlamaIndex · Mem0
Similar Projects
Developer Tools●●Solid
Aide-memory – persistent memory for AI coding agents and teams
Path-scoped memory beats project-wide rules files for team context sharing.
Solve My ProblemNiche Gem
ahmedmeky
402mo ago
AI/ML●●Solid
Eidentic – TypeScript SDK for AI agents with self-improving memory
Temporal knowledge graph memory and trace-to-test evals beat standard vector RAG.
Solve My ProblemBig Brain
baranozdemir
4027d ago
AI/ML●●Solid
RemembrallMCP – code dependency graph for agents and memory
Tree-sitter dependency graph saves 5,000-20,000 tokens per agent query vs exploration.
Big BrainSolve My Problem
cdnsteve
303mo ago
Developer Tools●●Solid
Agents Remember – Git-aware memory for coding agents
Git-verified memory ledger beats vague agent context files.
Big BrainNiche Gem
foxfire_1st
321mo ago
AI/ML●●●Banger
A benchmark for the failure modes of agent memory
Shows retrieval metrics lie—answer correctness ranges from 23% to 92% across identical scores.
Big BrainDark Horse
Pankhi123
1010d ago