AI/ML●●Solid
Breathe-Memory – Associative memory injection for LLMs (not RAG)
Graph-based context compression beats lossy summarization when tokens run out.
Big BrainNiche Gem
mvyshnyvetska
612mo ago
Back to browse
GitHub Repository
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
26,422 starsTypeScript
Local Context and Memory Stack
by dhravya·Jun 10, 2026·1 point·0 comments
AI Analysis
●●SolidBig BrainShip It
Tops LongMemEval and LoCoMo benchmarks with local-first AI memory architecture.
Strengths
- •Hybrid search combines RAG with memory in one query.
- •Connectors sync Google Drive and Notion via webhooks.
- •Multi-modal extractors handle PDF and OCR and AST chunking.
Weaknesses
- •AI memory layer is becoming crowded with funded competitors.
- •Self-hosting adds deployment complexity for teams.
Category
Target Audience
Developers building AI applications needing persistent context
Similar To
Mem0 · Zep · LangChain Memory
Similar Projects
AI/ML●●Solid
Mneme–Persistent memory for AI agents without vector search or RAG
Structured memory layers for agents—but vector search already solves this problem.
Big BrainShip It
xqli
143mo ago
AI/ML●Mid
Dropbox for Your Agents' Memories
Memory sync across Claude/ChatGPT, but unproven competitive advantage over session-scoped context.
Ship It
diwank
203mo ago
Developer Tools●●Solid
CogmemAi – Persistent memory and compaction recovery for Claude Code
Persistent memory for Claude Code with auto-compaction recovery—but relies entirely on external API.
Solve My ProblemNiche Gem
hifriendbot
123mo ago
AI/ML●Mid
MAItion – Open-source RAG with pluggable connectors and chat UI
Yet another RAG platform competing with Danswer, AnythingLLM, and Glean in a crowded space.
Ship It
vedmaka
101mo ago
Developer Tools●Mid
Modalyze – Modal Manager for React
Context-preserving modals are useful, but Mantine and Chakra already solve this adequately.
Ship It
kaundur
202mo ago