AI/ML●●Solid
Engram – open-source persistent memory for AI agents (Bun and SQLite)
SQLite-backed agent memory with graph viz when Mem0 and Zep already dominate.
SlickShip It
zanfiel
333mo ago
Back to browse
GitHub Repository
Auditable memory for agent teams. Self-hosted, deterministic retrieval, no LLM in the critical path. Python + MCP + Docker.
13 starsPython
Memwright – Self-hosted memory for multi-agent teams, no LLM in path
by Bolnet·Apr 15, 2026·3 points·0 comments
AI Analysis
●●SolidBig BrainNiche Gem
No LLM in the critical path — deterministic retrieval beats vector search latency.
Strengths
- •Sub-5ms retrieval claim with SQLite + pgvector + Neo4j hybrid architecture.
- •MCP server integration means agents can query memory without custom glue code.
- •Self-hosted design avoids sending agent state to third-party memory services.
Weaknesses
- •Agent memory is crowded — LangChain, LlamaIndex, and vector DBs already offer similar patterns.
- •Only 2 GitHub stars and 0.1 revision suggests early stage with unproven production use.
Category
Target Audience
Developers building multi-agent AI systems
Similar To
LangChain Memory · LlamaIndex · Zep
Similar Projects
AI/ML●●Solid
AFS – filesystem-native memory layer for AI agents
Putting the memory layer on-disk as a .afs/ tree is a gutsy, practical move — you get searchable JSON, FTS5 for text queries, HNSW vectors for similarity, and msgpack edges for relationships without running a separate DB service. It feels like a thoughtful toolkit for agents that must persist thinking artifacts (observations → reflections → knowledge), though I want to see details on concurrency, index portability, and how this performs at scale before betting production workloads on it.
Big BrainBold Bet
thompson0012
204mo ago
Developer Tools●●●Banger
Agent Recall – Open-source, local memory for AI agents (SQLite/MCP)
Scope-hierarchical memory for agents across projects—Mem0 and Zep flatten context too much.
Solve My ProblemBig Brain
MaxNardit
123mo ago
AI/ML●●Solid
Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)
Knowledge graph memory beats pure vector search, but Mem0 and LangChain already own this space.
Big BrainShip It
zaydmulani
603117d ago
Developer Tools●●Solid
LedgerMind – true zero-touch autonomous memory for AI agents
Autonomous memory healing every 5 min, but Mem0 and LangGraph already solve this.
Big BrainShip It
sl4m3
203mo ago
AI/ML●●●Banger
Mnemora – Serverless memory DB for AI agents (no LLM in your CRUD path)
Removes LLM from memory CRUD path—sub-10ms reads beat Mem0/Zep's 200-500ms by design.
Big BrainSolve My ProblemWizardry
isaacgbc
443mo ago