SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 TypeScript Memory Projects
-
Project mention: AirLLM Shrinks 70B LLMs to 4GB VRAM; DPO & Supermemory Boost Open Models | dev.to | 2026-06-03
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
12-factor-agents
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Own your control flow! A key point from 12 factor agents.
"One thing that I have seen in the wild quite a bit is taking the agent pattern and sprinkling it into a broader more deterministic DAG." - https://github.com/humanlayer/12-factor-agents/blob/main/REA...
-
Project mention: Show HN: Mnemo – local-first AI memory layer for any LLM (Rust, SQLite,petgraph) | news.ycombinator.com | 2026-06-03
-
MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings (by MemTensor)
Project mention: Top 10 OpenClaw Development Patterns and Architecture Best Practices | dev.to | 2026-02-18Repository: https://github.com/MemTensor/MemOS Architecture Pattern: Layered Memory System
-
Understand-Anything
Graphs that teach > graphs that impress. Turn any code, or knowledge base (Karpathy LLM wiki), into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
Project mention: Understand Anything – Graphs that teach the codebase | news.ycombinator.com | 2026-05-26 -
-
byterover-cli
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
Cipher https://github.com/campfirein/cipher
-
OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Project mention: Show HN: A local-first memory store for LLM agents (SQLite) | news.ycombinator.com | 2025-12-14edit:
from gpt5.2 with prompt:
<< 'adversarial review request. please look at the github link for signs of being written by llm ( extra points if you can point to the llm that generated it ) https://github.com/CaviraOSS/OpenMemory'
>> I can’t prove it’s LLM-written from the outside, but the README (at least) has a lot of “LLM smell.” I’d put it at high likelihood of AI-assisted marketing/docs copy, with some sections bordering on “generated then lightly edited.”
but then it adds a list of style reason why it could be generated by llm
<< “Extra points”: which LLM wrote it?
Most likely: Claude 3.5 Sonnet–style output
<< if i were to point to comments in readme and code, what would you say upon re-review
>> Comments that narrate the obvious (especially line-by-line)
-
Project mention: Testing a Filesystem Service with memfs + FakeWatchService: No Disk Required | dev.to | 2026-04-27
memfs is a fully in-memory fs implementation. Its API is identical to Node.js's native fs, but everything happens in memory — no disk touched.
-
Agentset
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
Project mention: Ask HN: What Are You Working On? (February 2026) | news.ycombinator.com | 2026-02-08https://agentset.ai/
Open-source RAG infrastructure.Every team I talk to has the same experience: RAG works in the demo, breaks in production.
We handle ingestion through retrieval with optimizations baked in. 97.9% on HotpotQA vs 88.8% for standard RAG. Model-agnostic, 22+ file types, built-in citations, MCP server. MIT licensed.
https://github.com/agentset-ai/agentset
-
-
-
-
cavemem
Cross-agent persistent memory for coding assistants. Stored compressed. Retrieved fast. Local by default.
Project mention: Why I’m Cautious About AI Gateways After My Bifrost Collaboration | dev.to | 2026-04-29🪨 Caveman Ecosystem · caveman talk less (you are here) · cavemem remember more · cavekit build better
-
Grov
Grov automatically captures the context from your private AI sessions and syncs it to a shared team memory. It auto injects relevant memories across developers and future sessions to save tokens and time spent on tasks.
Project mention: Show HN: Grov – Multiplayer for AI Coding Agents (Open Source) | news.ycombinator.com | 2026-01-21 -
recall
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the managed SaaS at recallmcp.com.
Project mention: Show HN: Recall – Persistent Memory for Claude Code via MCP Hooks | news.ycombinator.com | 2026-02-27Hooks are pure bash + curl. No daemon, no npm packages, no background processes. Every hook exits 0 on errors so it never blocks Claude.
Memory is stored in Redis with semantic search via embeddings (Voyage AI, Cohere, OpenAI, or others). Each tenant gets isolated storage with AES-256-GCM encryption.
Some features that might be interesting to this audience:
1. Native Claude Code plugin — ships as a proper plugin installable with `/plugin install recall@claude-plugins-official`. Bundles MCP server config + all 4 hooks. Auto-updates in the background.
2. Webhook ingestion — route GitHub/Stripe/any webhook into a Claude session. Your AI becomes event-aware.
3. Self-hosted — `curl -fsSL https://install.recallmcp.com | bash` gives you a Docker Compose stack with Redis + Recall. $12/mo license, air-gapped compatible.
4. Team sharing — one Claude learns, all team Claudes know. Workspace-scoped with selective sharing.
Open source (MIT): https://github.com/joseairosa/recall
-
AgentOS
Build autonomous AI agents with adaptive intelligence and emergent behaviors to simulate any scenario. Multimodal RAG included. (by framersai)
Project mention: Show HN: Paracosm – simulate what-if scenarios with AI agents | news.ycombinator.com | 2026-05-05 -
vault-operator
Real AI agent for your vault. Coworker, Copilot & thinking partner, that maintains your memory & knowledge, adapts to your workflows, uses plugins, skills & tools with full safety controls. BYOK & MCP. (by pssah4)
Project mention: Karpathy LLM Wiki pattern integrated into Obsidian agenic workflow | news.ycombinator.com | 2026-05-31 -
mnemosyne
Cognitive Memory OS for AI Agents — persistent, self-improving, multi-agent memory (by 28naem-del)
Project mention: We Built the First AI Agent Memory System With Zero LLM Calls — Here's the Architecture | dev.to | 2026-02-24Website: mnemosy.ai
-
kinbot
Self-hosted AI agents with persistent memory, real identity, and collaboration. One process, one SQLite file, zero cloud.
Project mention: Show HN: KinBot – Self-hosted AI agents that build their own web apps | news.ycombinator.com | 2026-03-06Hey HN, I built KinBot because I was frustrated with AI tools that forget everything between sessions.
The core idea: you create "Kins," which are AI agents with persistent memory (vector + full-text search), real identity, and autonomy. They live on your server and remember every conversation.
What makes it different from other agent platforms:
- Mini Apps: Kins can build and serve their own web applications on the fly. Think of it as giving your agent a canvas to create interactive tools, dashboards, or utilities.
- Persistent memory: not just context window tricks, but actual long-term memory with hybrid search across months of conversations.
- Multi-agent collaboration: Kins can talk to each other, delegate tasks, spawn sub-agents.
- Runs anywhere: single process, SQLite, works on a Raspberry Pi. No Kubernetes cluster needed.
- 23 AI providers supported (OpenAI, Anthropic, Google, Ollama, etc.)
Tech stack: Bun + Hono on the backend, React + TailwindCSS on the frontend, SQLite for everything. One Docker command to run it.
I have been using it daily for months as my personal assistant setup. The mini-apps feature is what I find most exciting: instead of just chatting, your agents can actually build things you interact with.
Looking for feedback on: the mini-apps concept, the memory architecture, and whether the self-hosting story is compelling enough. Happy to discuss technical details.
Repo: https://github.com/MarlBurroW/kinbot
-
robrain
Open-source shared memory for teams using AI agents. Captures every decision and the alternatives your team ruled out, and flags when a new decision contradicts an old one — so your team revisits past decisions intentionally, instead of re-litigating from zero.
Project mention: Show HN: RoBrain – Shared memory for AI agents, with rejected alternatives | news.ycombinator.com | 2026-05-19What's open source today (Apache 2.0): the capture pipeline, the Postgres schema with rejected[] as a first-class field, the lifecycle tracking, semantic + file-scoped retrieval, and a Synthesis batch job that scans the whole corpus for contradictions that the reactive path missed (e.g. session 12 says "all API calls must be idempotent," session 47 says "fire-and-forget for webhook delivery" — different files, never compared at insert time).
Honest comparisons in the README — including where Claude's built-in Auto Memory is genuinely enough (solo dev, single editor, young repo) and where the overhead pays off (teams, multiple editors, >6-month projects).
Repo: https://github.com/adelinamart/robrain
Would love feedback on the data model, the rejected[] schema specifically, and where the capture heuristics could be sharper. Happy to answer anything.
-
memory-powermem
openclaw(clawdbot) Plugin: give your bot long-term memory with PowerMem—smart extraction, Ebbinghaus recall, multi-agent isolation.
Project mention: I Raised a “Lobster” Assistant: It Burned Tokens, Not Electricity | dev.to | 2026-04-27 -
knowledgegraph-mcp
MCP server for enabling persistent knowledge storage for Claude through a knowledge graph with multiple storage backends and fuzzy search
Project mention: The AI-Native GraphDB + GraphRAG + Graph Memory Landscape & Market Catalog | dev.to | 2025-10-26KnowledgeGraph-MCP - github.com/n-r-w/knowledgegraph-mcp
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
TypeScript Memory discussion
TypeScript Memory related posts
-
I built persistent AI memory for Claude on Cloudflare's free tier
-
Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do
-
Testing a Filesystem Service with memfs + FakeWatchService: No Disk Required
-
Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File
-
Show HN: Grov – Multiplayer for AI Coding Agents (Open Source)
-
The Wipe & Inject Pattern: Full Context for Implementation After Long Planning Sessions
-
Show HN: Grov: Persistent memory for Claude Code sessions
-
A note from our sponsor - SaaSHub
www.saashub.com | 8 Jun 2026
Index
What are some of the best open-source Memory projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | supermemory | 25,415 |
| 2 | 12-factor-agents | 23,005 |
| 3 | agentmemory | 20,972 |
| 4 | MemOS | 9,615 |
| 5 | Understand-Anything | 8,502 |
| 6 | memlab | 4,971 |
| 7 | byterover-cli | 4,817 |
| 8 | OpenMemory | 4,190 |
| 9 | memfs | 2,062 |
| 10 | Agentset | 2,008 |
| 11 | space-radar | 1,441 |
| 12 | react-cool-virtual | 1,224 |
| 13 | ReMind | 510 |
| 14 | cavemem | 227 |
| 15 | Grov | 192 |
| 16 | recall | 168 |
| 17 | AgentOS | 117 |
| 18 | vault-operator | 88 |
| 19 | mnemosyne | 44 |
| 20 | kinbot | 43 |
| 21 | robrain | 25 |
| 22 | memory-powermem | 24 |
| 23 | knowledgegraph-mcp | 23 |
Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com