Tag
Agent memory tools
Persistent memory for agents. 17 reviewed tools: 17 free or open source.
Order: free and open source first, then hosted products with a real free tier, then paid-led; catalog order inside each group, with quiet or archived repos last. Not a score, and no tool pays for its place.
17 tools
- Mem0Memory infrastructure for AI agents that actually persists
Free / OSS · Freemium · 67.6k GitHub stars
VerdictThe memory layer most agent teams should use instead of building.
CatchExternal dependency for a core capability. Async processing adds latency. Platform optimizations are not in the open-source SDK. You are trusting Mem0 with potentially sensitive user data.
- LettaEpisodic memory for agents that think across sessions
Free / OSS · Apache-2.0 · 25.2k GitHub stars
VerdictThe memory architecture for agents that need to think long-term.
CatchMore complex to reason about than simple vector retrieval. The paging mechanism adds latency and orchestration overhead. Documentation assumes understanding of the original MemGPT paper.
- GraphitiApache-2.0 temporal knowledge graphs for agent memory; Zep's OSS engine
Free / OSS · Apache-2.0 · 32.1k GitHub stars
VerdictApache-2.0 temporal memory graphs. Free self-host; Zep Cloud is the paid path.
CatchFramework only — you run a graph DB + ops. Zep Community Edition deprecated; full Zep SaaS is separate (Free credits then Flex ~$104/mo billed annually). Not a drop-in chat history store. Schema/ops cost vs Mem0 Docker.
- EngramMIT persistent agent memory — MCP, CLI, TUI, SQLite
Free / OSS · OSS/MIT · 7.5k GitHub stars
VerdictMIT agent memory primitive. MCP/CLI/TUI on SQLite; not a full agent framework.
CatchVs Mem0 / Letta / full agent frameworks: Engram is the memory primitive (store + retrieve + surfaces), not an orchestration framework or coding agent. “local or cloud” branding means optional hosted/sync gravity — day-one stays OSS you run. You still decide what gets written and when.
- Atlas (pacifio)MIT multi-agent change tracking — source control for agents
Free / OSS · Apache-2.0 · 9.6k GitHub stars
VerdictMIT agent source-control. pacifio Atlas ≠ Ariga Atlas; track agents, not schemas.
CatchVs Worktrunk/jj (git worktree / change-oriented VCS plumbing): Atlas is agent session+change tracking with shared memory, not a general VCS replacement. name collision with Ariga Atlas (slug `atlas`, schema-as-code) — this card is `atlas-agents` / pacifio only; never confuse with atlasgo.io.
- ECCMIT agent ecosystem / coordination surface
Free / OSS · OSS/MIT · 285k GitHub stars
VerdictMIT agent coordination ecosystem. Skills+memory+security on top of host agents — not a host itself.
CatchStill depends on host agents (Claude Code / Codex / Cursor / etc.) — ECC coordinates and tunes the harness; it is not a replacement coding agent. Vs OpenSpec (spec-driven change tooling) and Thurbox (tmux multi-agent TUI): ECC is the skills/memory/security ecosystem pack, not a spec framework and not a pane orchestrator.
- oh-my-hermesMIT Hermes-agent niche tooling — memory & workflows
Free / OSS · OSS/MIT · 3.5k GitHub stars
VerdictMIT Hermes-agent tooling. Niche, not a multi-host skill pack.
CatchHermes-specific — not a generic Claude Code / Codex skill pack. Young surface; expect Hermes Agent as the host and follow upstream Hermes breaking changes. Vs ECC (multi-host ecosystem) and security-audit-skill (Cloudflare audit skill): oh-my-hermes is niche Hermes tooling, not a cross-harness coordination layer or a security scanner.
- FridaySelf-hosted cognitive memory MCP for coding agents
Free / OSS · OSS/MIT · 68 GitHub stars
VerdictMIT self-hosted memory MCP. Use when coding agents need durable local memory without Mem0 Cloud.
CatchVs Mem0 / Letta / Graphiti: Friday is the self-hosted MCP memory appliance for coding agents, not a multi-tenant memory API or a full agent OS. You operate Neo4j/Compose and embedding/model keys; star count is still early — pin and verify before production trust.
- SupermemoryMIT memory/context engine with a local API
Free / OSS · OSS/MIT · 31.3k GitHub stars
VerdictMIT memory/context engine. Fast local/API path; verify the paid self-host boundary before planning a hosted deployment.
CatchVs Mem0 / Letta / Graphiti: Supermemory leans into a local/API speed angle, not the same graph-orchestration shape. pricing caveat: the pricing page gates self-hosted deployments to paid tiers while the README documents a free local binary — read “self-host” as the OSS/local path, not a promise that every production deployment tier is free. You still own data policy and retrieval quality.
- OpenVikingAGPL self-evolving context database for memory, RAG, and skills
Free / OSS · AGPL-3.0 · 40.5k GitHub stars
VerdictAGPL-3.0 self-evolving context DB. Broad memory/RAG/skills surface; network copyleft is a deployment decision, not a footnote.
CatchAGPL-3.0 is strong copyleft, including the network-copyleft boundary when you modify OpenViking and offer it as a service. Get legal review before exposing a modified deployment over a network. Vs Mem0, Graphiti, and Letta: OpenViking is the context database spanning memory/RAG/skills, not simply a memory API, graph memory layer, or agent runtime.
- OKF Agent MemoryGit-native dual-memory for agents — OKF v0.2 + embedded MCP
Free / OSS · OSS/MIT · 826 GitHub stars
VerdictMIT git-native agent memory. Use when you want OKF bundles and MCP retrieval without another database.
CatchVs Engram / Mem0 / Supermemory / Letta: OKF is the git-native OKF+AAG dual-memory recipe with MCP, not a hosted memory SaaS or paging OS. You still author the Domain Codex and decide write discipline; empty knowledge/ stays empty.
- ai-memoryZero-LLM git-backed Markdown memory wiki with SQLite FTS
Free / OSS · OSS/MIT · 12k GitHub stars
VerdictMIT zero-LLM memory wiki. A compelling portable SoT for multiple harnesses; do not confuse it with the OKF Agent Memory or treat rapid stars as validation.
CatchVs OKF Agent Memory, OpenViking, and Supermemory: ai-memory is the akitaonrails cross-harness git/Markdown/SQLite source-of-truth path, not OKF's dual-memory bundle, a hierarchical context system, or a hosted memory API. ★~7.8k rapid growth is not proof the stars are organic or that retrieval quality fits your workload; audit the history and test recall before trusting it with durable facts.
- Codebase Memory MCPMIT persistent code knowledge graph MCP — static binary, no LLM key
Free / OSS · OSS/MIT · 47.1k GitHub stars
VerdictMIT local code-graph MCP when agents need structural queries without a server-side model key; audit the install path and treat the ★ spike as a signal, not proof.
CatchVs CodeGraph, Serena, and Supermemory: this is a persistent local code-graph MCP from a static binary, not an AST/MCP peer alone, an LSP-symbol MCP alone, or a general memory API. Default install is curl|bash; Microsoft Defender has false-positived release binaries (Wacatac-family); star velocity is extreme (~45k, repo created 2026-02) — verify checksums/VirusTotal links before trusting the pipeline.
- DeerFlowMIT long-horizon SuperAgent harness — sandboxes, memory, skills, gateway
Free / OSS · OSS/MIT · 84.2k GitHub stars
VerdictMIT SuperAgent harness when you want sandboxes + skills + gateway in one OSS tree and will bring models plus Docker headroom.
CatchVs OpenHands, LangGraph, and Mastra: DeerFlow is a full SuperAgent product harness with sandboxes/memory/gateway, not an open coding agent alone, a graph orchestration library, or a TypeScript workflow framework. BYO model API keys; Docker sizing is resource-heavy (multi-vCPU/GB guidance); star velocity is extreme (~83k).
- HindsightMIT retain→recall→reflect agent memory (+ MCP)
Free / OSS · OSS/MIT · 52.1k GitHub stars
VerdictMIT agent memory when you want retain→recall→reflect (+ MCP) you can self-host; keep Cloud optional and do not bet the stack on a single eval leaderboard.
CatchVs Mem0, Graphiti, Engram, and Supermemory: Hindsight is a retain/recall/reflect memory product with optional hosted Cloud/Enterprise, not a general memory SDK alone, a temporal knowledge graph, a local binary brain, or a speed-first memory API. Treat LongMemEval / SOTA marketing as vendor claims, not catalog proof; Cloud and Enterprise are upsell paths beside the OSS self-host bar.
- CogneeApache-2.0 AI memory platform — local knowledge graph for agents
Free / OSS · Apache-2.0 · 32.6k GitHub stars
VerdictApache agent memory when you want a local knowledge graph company brain — not Mem0 cloud seats, not Hindsight’s reflect product alone.
CatchVs Mem0 / Hindsight: Mem0 is freemium memory infra SDK/cloud; Hindsight is MIT retain→recall→reflect (+ MCP). Cognee’s catch is KG-first company/agent memory you self-host — not Mem0’s hosted memory API and not Hindsight’s reflect loop alone. Graph + embedding pipelines cost CPU/disk; hosted/cloud extras (if any) are optional beside the OSS bar.
- Obsidian MindMIT Obsidian vault as persistent agent memory
Free / OSS · OSS/MIT · 5.4k GitHub stars
VerdictThe most complete plain-Markdown memory setup for Claude Code and friends — free, but opinionated and Obsidian-bound.
CatchIt is opinionated about work life — standups, 1:1s, brag docs, incident capture — so it fits people who want an agent-run work journal, not just a project memory file. Needs Obsidian 1.12+ (a free but closed-source app) with its CLI enabled, plus Node 22+. QMD downloads about 2 GB of local models on first use. Hooks run on every session and message, so read them before you trust a vault. Vs mem0 or Letta: those are memory layers you build into an app; this is a personal vault for your own coding agent.
FAQ
- What is the top free pick among Agent memory tools?
- Mem0 leads the Stack Gems list for Agent memory tools. Verdict: The memory layer most agent teams should use instead of building.
- How many Agent memory tools does Stack Gems review?
- 17: 17 free or open source. Each review has a verdict and an honest Catch; no tool pays for its spot.
- Which Agent memory tools can I self-host for free?
- Letta, Graphiti, Engram, Atlas (pacifio), ECC, oh-my-hermes, Friday, Supermemory and 8 more.
- Which Agent memory tools have the most GitHub stars?
- ECC (285k), DeerFlow (84.2k), Mem0 (67.6k), per GitHub on 2026-10-21. Stars measure attention, not fit; read the Catch.
- What is the catch with Mem0?
- External dependency for a core capability.