Agentmemory logo

Agentmemory

For developers: Agentmemory gives Claude Code and coding agents searchable persistent memory, reducing token usage by 92% while keeping 100% of observations accessible.

Built by Rohit Ghumare · Artificial Intelligence · Developer Tools · Open Source · Free

Visit website

In category: #284 of 2048 · Artificial Intelligence

Agentmemory is a Product Hunt listing on Launch Llama with 253 total upvotes, founded by Rohit Ghumare who joined in May 2026, compared against 6 alternatives.

Product Hunt listing

Listing status

253upvotes

Community score

Rohit Ghumare (Joined May 2026)

Founder

Launched on Launch Llama May 17, 2026 · #14 of 36 that day

Agentmemory

Agentmemory screenshot 1Agentmemory screenshot 2Agentmemory screenshot 3Agentmemory screenshot 4Agentmemory screenshot 5

About

You can now give Hermes, Claude Code, and Codex infinite memory. Agentmemory is trending on GitHub with 5,000+ Stars. CLAUDE md dumps 22,000+ tokens into context at 240 observations agentmemory: 1,900 tokens. same observations. 92% less. At 1,000 observations, 80% of your built-in memories become invisible. agentmemory keeps 100% searchable. benchmarked on 240 real coding sessions → Up to 95% fewer tokens per session → 200x more tool calls before hitting context limits → 100% open source

Launch Llama's Take

Based on Launch Llama data as of

Agentmemory has 253 upvotes, including the votes it received on Product Hunt, which ranks it #284 of 2,048 Artificial Intelligence tools on Launch Llama by upvotes, in the top quarter. It has been listed on Launch Llama since May 2026. No Launch Llama members have upvoted it yet and it has no reviews yet.

Agentmemory vs ContextPool

Agentmemory gives Hermes, Claude Code, and Codex persistent memory across coding sessions, capturing them automatically through hooks. Where ContextPool extracts bugs, fixes, and design decisions from past sessions, Agentmemory consolidates raw observations into semantic memories when a session ends. PMB keeps its memory in one SQLite workspace on your disk, while Agentmemory runs entirely locally with zero external databases or dependencies.

Agentmemory vs ContextPool: side-by-side comparison
AgentmemoryContextPoolThe Agentic Coding KitMemori
What it doesFor developers: Agentmemory gives Claude Code and coding agents searchable persistent memory, reducing token usage by 92% while keeping 1…For AI coding teams: ContextPool gives your agent persistent memory by extracting bugs, fixes, and design decisions from past sessions an…For developers: The Agentic Coding Kit provides 34 preset files, subagents, and git hooks so Claude and Cursor follow your project conven…For AI engineers: Memori builds structured long-term memory from agent execution so you reduce inference costs by 95%.
PricingFreeFreemiumPaidFreemium
Free planYes, free to useYes, free planNo free plan listedYes, free plan
CategoryOpen SourceOpen SourceDeveloper ToolsOpen Source
Upvotes on Launch Llama25317467154
Listed on Launch LlamaMay 2026April 2026September 2026June 2026

See all Agentmemory alternatives

Key Features

  • Capture every coding session automatically with twelve hooks
  • Recall memories using hybrid search across lexical, semantic and graph scores
  • Consolidate raw observations into semantic memories on session end
  • Run entirely locally with zero external databases or dependencies
  • Access memories via MCP tools or REST endpoints

Use Cases

  • Coding agents that need context from previous sessions without bloating context windows
  • Claude Code and other MCP clients requiring persistent memory across work sessions

Who it is for

  • Developers using Claude Code, Cursor, Codex or similar coding agents who are tired of re-explaining their project each session.
  • Developers who want local, account-free long-term memory for AI coding agents without sending data to the cloud.
  • Engineering teams running several coding agents side by side who want one shared local memory server.

Pricing

Agentmemory is free to use. See the website for details.

View Agentmemory pricing →

FAQ

What does agentmemory actually store?

Observations from your agent's sessions: the prompts you typed, the tools it called and a bounded copy of their output, and the session summaries built from them. Consolidation turns related observations into memories, lessons and graph facts. Everything lives in a data folder on your machine, for example ~/Library/Application Support/agentmemory on macOS.

Does anything leave my machine?

Not by default. With no provider configured, recall runs on BM25 keyword search and nothing is sent anywhere. If you add an LLM or an embedding provider, agentmemory sends that provider the text it needs. Local embeddings send nothing. There is no telemetry.

Do I need an API key?

No. Keyless mode works out of the box with BM25 recall. Set EMBEDDING_PROVIDER=local for free on-device semantic recall, or add a provider key for LLM consolidation.

Which agents does it work with?

Any MCP client. Claude Code, Codex CLI, Copilot CLI, Cursor, OpenCode, Devin and others get native plugins with hooks that capture automatically. Run agentmemory connect to wire one.

What happens if the server crashes mid-session?

Hooks write to an offline spool while the server is down and drain it when it comes back. Each event has a restart-safe id, so replays are stored once. Vectors survive a crash through a pending log. Every publish runs a release gate that force-kills the installed package and checks nothing was lost.

How is it licensed?

Apache-2.0. The whole runtime is open source, including the parts that run on your machine. There is no hosted tier and no feature held back.

Alternatives

The Agentic Coding KitFor developers: The Agentic Coding Kit provides 34 preset files, subagents, and git hooks so Claude and Cursor follow your project conventions instead of ignoring them.MemoriFor AI engineers: Memori builds structured long-term memory from agent execution so you reduce inference costs by 95%.PMBFor AI coding users: PMB gives Claude, Cursor, and Zed persistent project memory so agents understand your codebase without re-explanation.Agent IslandFor developers: Agent Island monitors Claude, Codex, Grok, and Cursor sessions locally so you track AI coding progress without telemetry.AgentKeyFor AI agents: AgentKey connects Claude, Codex, and MCP agents to live search, finance, social, and e-commerce data instantly so workflows access real-time information without manual integrations.ContextPoolFor AI coding teams: ContextPool gives your agent persistent memory by extracting bugs, fixes, and design decisions from past sessions and loading relevant context automatically.

More in Artificial Intelligence

All Artificial Intelligence tools

New on Launch Llama

Launched this week · This month's launches · All products A–Z

Tags

#persistent memory#token reduction#coding agents#claude code#semantic search#session capture#mcp tools#local first

Ask AI about Agentmemory

ChatGPT Claude Perplexity Grok

For bots & AI agents

Machine-readable versions of Agentmemory and Launch Llama. Fetch these instead of parsing this page.

This listing (.md) llms.txt llms-full.txt ai.txt Full catalog (.md) Endpoint index API docs MCP server MCP manifest Developer docs