AI · alternatives · 2026
24 alternatives to A local-first memory store for LLM agents (SQLite)
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. - CaviraOSS/LongMemory
This is a local-first memory storage system built on SQLite, designed specifically for LLM agents to store and retrieve information. It runs locally on a user's machine rather than relying on cloud services, giving… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
Agentmemory▲310Persistent memory for Claude Code, Codex & coding agents
May 2026 · agent-memory.dev · its alternatives →
- 2
Built this for my LLM workflows - needed searchable, persistent memory that wouldn't blow up storage costs. I also wanted to use it locally for my research. It's a content-addressed storage system with block-level deduplication (saves 30-40% on typical codebases). I have integrated the CLI tool into most of my workflows in Zed, Claude Code, and Cursor, and I provide the prompt I'm currently using in the repo. The project is in C++ and the build system is rough around the edges but is tested on macOS and Ubuntu 24.04.
2025 · github.com · its alternatives →
- 3
PMB▲211PMB gives Claude Code, Cursor, Codex and Zed a real memory. Decisions, lessons and facts in one SQLite file on your disk. Offline, no API keys, no cloud.
Jun 2026 · pmbai.dev · its alternatives →
- 4
- 5
I keep running in the same problem of each AI app “remembers” me in its own silo. ChatGPT knows my project details, Cursor forgets them, Claude starts from zero… so I end up re-explaining myself dozens of times a day across these apps. The deeper problem 1. Not portable – context is vendor-locked; nothing travels across tools. 2. Not relational – most memory systems store only the latest fact (“sticky notes”) with no history or provenance. 3. Not yours – your AI memory is sensitive first-party data, yet you have no control over where it lives or how it’s queried. Demo video:…
2025 · 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
Claude-Mem▲115AI agent memory, everywhere. claude-mem is open-source memory for Claude Code; cmem links it to any MCP client — Cursor, Codex, more — via one private link.
Dec 2025 · cmem.ai · its alternatives →
- 8
GPS▲83Memory layer for LLMs that stores repo rules + past lessons
May 2026 · github.com · its alternatives →
- 9
Local-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
Jun 2026 · github.com · its alternatives →
- 10
- 11
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 →
- 12
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 →
- 13
The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite memory engine for Google Antigravity, Claude Code, Cursor, and Windsurf. Zero cloud lock-in. - timgordontg/engrim
Sep 2026 · github.com · its alternatives →
- 14YP
It's an biological inspired decay system for our memories with extended support of temporal reasoning. Created a CLI command to infer knowledge from the context stored in memory system without any token utilization or llm call. It comes with a memory dashboard to monitor and manage your memories it can be extended as audit trail for agents as well !
May 2026 · its alternatives →
- 15
This is a small library for giving an agent persistent memory without running any infrastructure. The whole store is one SQLite file, and the default install has no dependencies. I built it because whenever I wanted an agent to remember a handful of facts across sessions, the options were a hosted API, a vector database, or a framework, and that felt like too much for what is usually a few thousand short strings. The part I find most useful is that recall is deterministic, so you can write unit tests that assert what your agent remembers and run them in CI. I haven't seen that elsewhere and…
Aug 2026 · github.com · its alternatives →
- 16
hi HN, While building Wolbarg (an open-source shared memory SDK for AI agents), I assumed PostgreSQL would be the obvious choice for memory storage. After benchmarking SQLite under realistic agent workloads, I was surprised by the results. For local-first and single-node deployments, SQLite handled far more than I expected while keeping the architecture much simpler. I wrote up the benchmarks, methodology, trade-offs, and where I still think PostgreSQL is the better choice.
Jul 2026 · wolbarg.com · its alternatives →
- 17
I have a proposal that addresses long-term memory problems for LLMs when new data arrives continuously (cheaply!). The program involves no code, but two Markdown files. For retrieval, there is a semantic filesystem that makes it easy for LLMs to search using shell commands. It is currently a scrappy v1, but it works better than anything I have tried. Curious for any feedback!
Apr 2026 · github.com · its alternatives →
- 18
Markdown based AI agent memory with semantic search, hybrid retrieval, and offline-first sync between agents. - sqliteai/sqlite-memory
Apr 2026 · github.com · its alternatives →
- 19
Wannabe Main Memory Database and More. Contribute to ademakov/MainMemory development by creating an account on GitHub.
2017 · github.com · its alternatives →
- 20
Shared persistent memory across all your LLMs.
2025 · teamlayer.xyz · its alternatives →
- 21
Talamus▲3Durable local-first memory for AI agents, with citations
Jul 2026 · github.com · its alternatives →
- 22
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 →
- 23
I got tired of repeating myself to my LLM every session. rekal is an MCP server that stores memories in SQLite and retrieves them with hybrid search (BM25 + vectors + recency decay). One file, local embeddings, no API keys.
Apr 2026 · github.com · its alternatives →
- 24LS
Hi HN, I built llm.sql, an LLM inference framework that reimagines the LLM execution pipeline as a series of structured SQL queries atop SQLite. The motivation: Edge LLMs are getting better, but hardware remains a bottleneck, especially RAM (size and bandwidth). When available memory is less than the model size and KV cache, the OS incurs page faults and swaps pages using LRU-like strategies, resulting in throughput degradation that's hard to notice and even harder to debug. In fact, the memory access pattern during LLM inference is deterministic - we know exactly which weights are needed…
Apr 2026 · its alternatives →
Also compare
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 →