Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise. Learn more →
Top 23 TypeScript agent-memory Projects
-
supermemory
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
bitterbot-desktop
Bitterbot - a mesh of agents that turns shared experience into collective capability.
Project mention: Bitterbot – A local-first P2P AI agent engine with persistent memory | news.ycombinator.com | 2026-09-16 -
Project mention: Show HN: Agent harness that turns errors into shared genes | news.ycombinator.com | 2026-04-21
-
swarmvault
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
-
Ori-Mnemos
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
-
pragma
Build portable agent teams across models and harnesses, with shared memory, skills, tools, and workflows — then bring them into Codex, Claude Code, or any AI system you build. 构建跨 harness 和模型的可移植 Agent Team，共享记忆、技能、工具和工作流，一次构建，接入 Codex、Claude Code 或任何 AI 系统。 (by pqpo)
Project mention: Show HN: Pragma – Stop copying context between AI agents | news.ycombinator.com | 2026-08-11 -
prism-coder
The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learning, ACT-R spreading activation, adversarial evaluation, persistent memory, multi-agent Hivemind and visual dashboard. Zero API keys required.
Project mention: Show HN: Prism Coder – Qwen3.5-14B fine-tuned for MCP tool-routing decisions | news.ycombinator.com | 2026-05-20 -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
argentos-core
Your own AI operating system. Self-hosted. Self-improving. One continuous, truthful, self-directed mind.
Project mention: I Was Engineering Around AI Emotions Before Anyone Proved They Existed | dev.to | 2026-04-02I've been building ArgentOS — a self-hosted, intent-native AI operating system that runs 29 specialized agents with persistent memory, autonomous cognition cycles, and a governance layer. For months, I've been diagnosing and engineering around exactly the dynamics Anthropic just proved exist. I didn't have the neuroscience. I had the operational evidence.
-
knowl
Persistent memory for Claude Code, Cursor and Codex. Facts are typed, sourced, and retired when they change. Local SQLite, no API keys.
Project mention: Show HN: Knowl – agent memory with write-time supersession, 0.90 on MAB | news.ycombinator.com | 2026-08-27Hey HN.
Open-source version at: https://github.com/dat999zx/knowl
The number is FactConsolidation single-hop at 262K context on MemoryAgentBench. On multi-hop Knowl scored 0.07 against an all-time ceiling of 0.14.
Write-up of the approaches that failed first: https://blog.knowl.cloud/the-story-of-knowl
-
signetai
Local-first identity, memory, and secrets for AI agents. Portable state across models and harnesses.
Project mention: Identity, memory, secrets that survive model switch | news.ycombinator.com | 2026-06-18 -
Project mention: Show HN: Instar – Persistent Server for Claude Code with Telegram and Evolution | news.ycombinator.com | 2026-03-17
-
markus
Not another agent framework — an operating system for AI workforces. Autonomous agents coordinate, remember across sessions, review each other's work, and deliver while you sleep. One command. Zero dependencies. Manage your AI company from your phone. (by markus-global)
Project mention: Building AI Digital Employees with Markus: An Open-Source Platform for Agent Teams | dev.to | 2026-05-21Star the repo: https://github.com/markus-global/markus Join the community: https://markus.global
-
Kage
Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install (by kage-core)
Project mention: Show HN: Kage, a framework to maintain and verify Google's OKF agent memory | news.ycombinator.com | 2026-07-01 -
claude-map-reduce-memory
Global, unlimited persistent memory for Claude Code agents. Context-activated hints injected automatically via hooks using scatter-gather map-reduce.
Project mention: Show HK: Fixing Claude Code's amnesia with persistent memory | news.ycombinator.com | 2026-03-31 -
ZenBrain
Dynamic agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS spaced repetition and memory consolidation. Zero-dependency TypeScript library, Model Context Protocol (MCP) server, Vercel AI SDK middleware. Paper: arXiv 2604.23878 · reproduction packages on Zenodo.
Project mention: 7-Layer Memory Architecture: How ZenBrain Remembers Like a Human Brain | dev.to | 2026-07-19GitHub: github.com/zensation-ai/zenbrain
-
commitlore
Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface only the decisions still in force.
Project mention: Show HN: CommitLore – Git memory for decisions coding agents keep forgetting | news.ycombinator.com | 2026-08-18 -
motif
The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning. (by motif-Labs)
Project mention: Show HN: I turned my team's coding-agent history into a knowledge graph | news.ycombinator.com | 2026-09-28 -
memforge
Neuroscience-inspired memory for AI agents — sleep cycles that rewrite and strengthen knowledge over time. TypeScript, PostgreSQL, MCP.
Project mention: Show HN: Self-improving agent memory system, 92% R 5 LongMemEval, PostgreSQL | news.ycombinator.com | 2026-04-08 -
bhived-mcp
bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.
-
Vitrus-Archive
your glass-box company brain — tells you what it doesn't know (deterministic gap analysis). MIT core · MCP · PGLite→Postgres.
Project mention: Show HN: Vitrus – the company brain that tells you what it doesn't know | news.ycombinator.com | 2026-06-20 -
TeamBrain
The brain is a git repo. Memories are markdown files with YAML front-matter, committed like any other file. Git history is the audit trail; pull requests are the approval gate — nothing is written to the shared brain without human review.
Project mention: Show HN: Capn-hook for coding agents – don't grep the same mystery twice | news.ycombinator.com | 2026-07-12I build something a litle bit different check it here: https://github.com/donatienmigue/TeamBrain
-
token-warden
Claude Code plugin that makes coding agents measurably cheaper over time: collect token costs, distill candidate rules, benchmark them on a frozen golden suite, and keep only rules that earn their context rent.
Project mention: I built a Claude Code plugin that only keeps an "agent memory" rule if it can prove it saves tokens | dev.to | 2026-06-27 -
Project mention: Memory Crystal – persistent memory for AI agents (MIT) | news.ycombinator.com | 2026-03-27
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
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 agent-memory discussion
TypeScript agent-memory related posts
-
Bitterbot – A local-first P2P AI agent engine with persistent memory
-
Show HN: Agent-hop – a Rust TUI that hops a live Claude Code chat into Codex
-
7-Layer Memory Architecture: How ZenBrain Remembers Like a Human Brain
-
Show HN: Kage, a framework to maintain and verify Google's OKF agent memory
-
Show HN: Kage, verification and freshness for Google's OKF agent memory
-
I built a Claude Code plugin that only keeps an "agent memory" rule if it can prove it saves tokens
-
Claude plugin that only keeps an "agent memory" rule and proves it saves tokens
-
A note from our sponsor - AppSignal
www.appsignal.com | 6 Oct 2026
Index
What are some of the best open-source agent-memory projects in TypeScript? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | supermemory | 31,058 |
| 2 | bitterbot-desktop | 2,462 |
| 3 | PrismerCloud | 1,554 |
| 4 | swarmvault | 708 |
| 5 | Ori-Mnemos | 328 |
| 6 | pragma | 202 |
| 7 | prism-coder | 132 |
| 8 | argentos-core | 126 |
| 9 | knowl | 123 |
| 10 | signetai | 119 |
| 11 | instar | 80 |
| 12 | markus | 47 |
| 13 | Kage | 38 |
| 14 | claude-map-reduce-memory | 29 |
| 15 | ZenBrain | 25 |
| 16 | commitlore | 18 |
| 17 | motif | 18 |
| 18 | memforge | 14 |
| 19 | bhived-mcp | 14 |
| 20 | Vitrus-Archive | 13 |
| 21 | TeamBrain | 13 |
| 22 | token-warden | 13 |
| 23 | memorycrystal | 12 |
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com