AI · alternatives · 2026
24 alternatives to A memory database that forgets, consolidates, and detects contradiction
Vector databases store memories. They don't manage them. After 10k memories, recall quality degrades because there's no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier. YantrikDB is a cognitive memory engine — embed it, run it as a server, or connect via MCP. It thinks about what it stores: consolidation collapses duplicate memories, contradiction detection flags incompatible facts, temporal decay with configurable half-life lets unimportant memories fade like human memory does. Single Rust binary. HTTP + binary wire protocol. 2-voter + 1-witness HA…
YantrikDB is a memory management system for AI agents that addresses vector database limitations by consolidating duplicate memories, detecting contradictions, and applying temporal decay to fade unimportant… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
Hey 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…
2025 · github.com · its alternatives →
- 2
The portable vector database for AI agents beyond the cloud
Apr 2026 · actian.com · its alternatives →
- 3
An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. - fellowgeek/mcp-memory
Aug 2026 · github.com · its alternatives →
- 4
Hey HN, we want to share HelixDB (https://github.com/HelixDB/helix-db/), a project a college friend and I are working on. It’s a new database that natively intertwines graph and vector types, without sacrificing performance. It’s written in Rust and our initial focus is on supporting RAG. Here’s a video runthrough: https://screen.studio/share/szgQu3yq. Why a hybrid? Vector databases are useful for similarity queries, while graph databases are useful for relationship queries. Each stores data in a way that’s best for its main type of query (e.g.…
2025 · github.com · its alternatives →
- 5
Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning. This implementation experiments with a biological approach by using the Ebbinghaus forgetting curve to manage context as a living substrate. Memories are assigned a "strength" score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned. To solve the…
Apr 2026 · github.com · its alternatives →
- 6
YourMemory▲93This is a project that I have been building for a while now, YourMemory is a solution to agentic memory which focuses on pruning of noise rather than hoarding of data. In the current state of agentic memory most of the context is stored in the form of a MD file or is derived through a RAG model where you store each and everything. Both of the solution leads to bloated context which does not optimize the usage of any tokens. In this system we only keep relevant data in our memory and prune all the unnecessary data. The relevance of a data is derived through multiple factors such as recall…
Apr 2026 · yourmemoryai.vercel.app · its alternatives →
- 7
Memori▲168Persistent memory from agent trace, not just conversation
May 2026 · memorilabs.ai · its alternatives →
- 8
Extremely memory-efficient vector database. Contribute to D-Star-AI/minDB development by creating an account on GitHub.
2024 · github.com · its alternatives →
- 9
- 10
Memoriq▲130Archive and search saved conversations from ChatGPT, Claude, Gemini, and Grok in one encrypted AI chat vault.
Jun 2026 · memoriq.me · its alternatives →
- 11
I've been working on Polign and built a small prototype around something I've been thinking about with agent memory. I have built a lightweight/stateless vector db + BM25 search which works really well with typed facts and structured queries. It uses your own S3, or GCS bucket as primary storage, and restarting a node is fairly quick. Demo + writeup: https://polign.com/blog-edge-agent-memory Live search demo: https://demo.polign.com Docs: https://polign.com
Aug 2026 · polign.com · its alternatives →
- 12
DeltaMemory▲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.
Feb 2026 · deltamemory.com · its alternatives →
- 13
Lossless long-term memory for a personal AI: never summarize, keep every line, put a timestamp on everything. - aru-labs/lossless-memory
Sep 2026 · github.com · its alternatives →
- 14
Hi everyone, I’m Timo, one of the creators of SuperDuperDB ! Today we are officially launching SuperDuperDB, an open-source framework for integrating AI directly with major databases, including streaming inference, scalable model training, and vector search, with release of v0.1. on GitHub and on ProductHunt. SuperDuperDB is not a database. It transforms your favorite database into an AI development and deployment environment (𝘮𝘢𝘬𝘪𝘯𝘨 𝘪𝘵 𝘴𝘶𝘱𝘦𝘳-𝘥𝘶𝘱𝘦𝘳). SuperDuperDB eliminates complex MLOps pipelines, specialized vector databases - and the need to migrate and duplicate data by…
2023 · github.com · its alternatives →
- 15
Tired of AI coding tools that forget everything between sessions? Every time I open a new chat with Claude or fire up Copilot, I'm back to square one explaining my codebase structure. So I built something to fix this. It's called In Memoria. Its an MCP server that gives AI tools persistent memory. Instead of starting fresh every conversation, the AI remembers your coding patterns, architectural decisions, and all the context you've built up. The setup is dead simple: `npx in-memoria server` then connect your AI tool. No accounts, no data leaves your machine. Under the hood it's TypeScript +…
2025 · github.com · its alternatives →
- 16
Tell MemorySync a fact, reload the page, then ask for it back in your own words. No signup. Every API call shown in cURL, Python and Node.js.
8d ago · memorysync.io · its alternatives →
- 17VA
Hey HN, At Mintplex Labs are building developer tools for AI applications. One area we encountered frustration was the use of Vector Databases like Pinecone, Chroma, QDrant, or Weaviate to "unlock" long-term memory and contextual answers. It is nearly impossible to manage this data when in use for production. The craziest thing was how you cannot atomically CRUD any vectors in most of these vector databases. Let alone easily copy, clone, or migrate data or entire indexes without paying for re-embedding - among other things. With VectorAdmin you get a database level UI with the ability to…
2023 · vectoradmin.com · its alternatives →
- 18
- 19
- 20
DriftDB - An experimental append-only database with built-in time travel. Query any point in history, guaranteed data integrity, and immutable audit trails. Written in Rust. - DavidLiedle/DriftDB
2025 · github.com · its alternatives →
- 21
OctaneDB is an open-source vector database for Python that focuses on ultra-fast similarity search for high-dimensional data—perfect for AI/ML, semantic search, and large-scale document or embedding retrieval. What does it do? Store, index, and search millions of embeddings (text, images, etc.) with sub-millisecond query time. Supports in-memory and efficient HDF5 persistent storage. Integrates seamlessly with sentence-transformers for automatic text embedding. Key Features: 10x faster than Pinecone or ChromaDB for vector search and batch insertions. Advanced indexing: HNSW (approximate…
2025 · github.com · its alternatives →
- 22
Hey, everyone. I am currently working on AllyDB, which is basically my own Redis, which I am writing in Elixir. Currently, the database is nowhere close to being ready, as you can see in the roadmap, but I am doing my best to add stuff as fast as possible. Currently the implementation is very simple, with an in memory table, an append log persistence system, as well as an interval persistence system as a backup. The database could definitely be optimized further, especially when it comes to persistence, which I am planning to do in the future. I'm also planning to use Rust NIFs for specific…
2023 · github.com · its alternatives →
- 23
Semantic search alone is not enough to capture all connected facts, they will capture the semantically most identical memory only. Tested on HotpotQA public dataset: Vector + BM25 + entity graph: BothFound@5 71.5% Vector + BM25 only: BothFound@5 59.5% Entity graph is the game changer to extract connected facts. More Benchmark result: LongMemEval-S: 84.8% recallAll@5 LoCoMo-10: 59% vs zep cloud 28% What is your approach for connected facts retrieval ?
Jul 2026 · yourmemoryai.xyz · its alternatives →
- 24
Also compare
- I replaced vector databases with Git for AI memory (PoC) alternatives
- Actian VectorAI DB alternatives
- MCP Memory – Fast Agent Memory Using Google's OKF and SQLite FTS5 alternatives
- HelixDB – Open-source vector-graph database for AI applications (Rust) alternatives
- AI memory with biological decay (52% recall) alternatives
- YourMemory alternatives
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →