MemoryOS
Hybrid AI Memory: Vector RAG meets Knowledge Graphs
MemoryOS launched on April 27, 2026 with 3 votes, #2,709 of 21,248 launches that month and more than 50% of that year's launches.
What it does
Most AI memory relies on Vector RAG, which lacks structural context. MemoryOS is a hybrid knowledge base that runs Vector Search and Graph Traversal in parallel. Using recursive SQL CTEs, it finds relational links that standard RAG misses—like discovering "HNSW" when you only query "indexing." It features a real-time Retrieval Inspector, UMAP semantic cluster maps, and an MCP server to connect your local knowledge memory directly to any AI assistant like Claude or ChatGPT.
MemoryOS is a powerful personal knowledge base that combines traditional **RAG (Vector Search)** with a **High-Fidelity Knowledge Graph**. It doesn't just store your notes; it understands the structural, causal, and semantic relationships between your ideas. - CommonCapital/MemoryOS
Does a similar job
all alternatives →
I replaced vector databases with Git for AI memory (PoC)2025 · github.com · ▲198Hey HN! I built a proof-of-concept for AI memory using Git instead of vector databases. The insight: Git already solved versioned document management. Why are we building complex vector stores when we could just use markdown files with Git's built-in diff/blame/history? How it works: Memories stored as markdown files in a Git repo Each conversation = one commit git diff shows how understanding evolves over time BM25 for search (no embeddings needed) LLMs generate search queries from conversation context Example: Ask "how has my project evolved?" and it uses git diff to show actual…
DeltaMemoryFeb 2026 · deltamemory.com · ▲104Most AI agents forget everything between sessions. We built DeltaMemory to fix that. It's a cognitive memory layer that gives agents persistent recall, automatic fact extraction, and temporal reasoning — via a single SDK call. Key numbers: - 89% accuracy on LoCoMo long-term conversation benchmark - 50ms p50 retrieval latency - 97% cost reduction vs raw token re-processing Open source SDKs, works with any LLM stack. Currently in early access. Happy to answer questions about the architecture, benchmark methodology, or how we handle knowledge graphs.
Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph)Jun 2026 · github.com · ▲60Local-first AI memory layer for any LLM. Persistent knowledge graph, entity extraction, semantic retrieval. Works with Ollama, OpenAI, Anthropic, or any OpenAI-compatible backend. - zaydmulani09/mnemo
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Product Hunt launch ↗
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app