AgentScout / Best lists / Claude-Mem alternatives

Claude-Mem alternatives (2026)

Claude-Mem is a coding tool: Gives coding agents memory across sessions by capturing what they do, compressing it and feeding the relevant context back in later. Pricing, as the maker states it: Open source. Its GitHub repo has 101,230 stars. We found 141 tools in the directory that do overlapping work (writing code, memory for agents); 106 of them are open source and 9 list a free or freemium plan. Below are the 10 closest, ranked by how many tasks and sub-tasks they share with Claude-Mem, then by GitHub stars.

  1. Context Mode (Source-available): Context window optimizer for coding agents that sandboxes tool output and persists session memory. Consider it because it also covers codebase context and code search and sandboxes and secure execution.
  2. AgentMemory (Open source): Persistent memory layer for AI coding agents. Consider it because it does the same job with a different approach (open source).
  3. Beads (Open source): Issue-tracking memory for coding agents so they can keep track of long-running work. Consider it because it also covers planning and task tracking.
  4. MiMo Code (Open source): Xiaomi's terminal coding agent with persistent project memory across sessions; works with any major model provider and is tuned for Xiaomi's MiMo models. Consider it because it also covers terminal and CLI agents.
  5. LazyCodex (Open source): Agent harness for Codex that adds project memory, planning, execution and verified completion for complex codebases. Consider it because it also covers codebase context and code search and planning and task tracking.
  6. Compozy (Open source): Operating system for AI agents that turns Claude Code, Codex, Gemini CLI and Cursor into a team with task handoff, loops, jobs and shared memory. Consider it because it also covers terminal and CLI agents.
  7. Dosu (See site): Knowledge infrastructure that keeps docs, specs and agent memory current with your code for teams and coding agents. Consider it because it is ready to use without building anything.
  8. opencode (Open source): Open-source terminal coding agent that works with many model providers. Consider it because it also covers terminal and CLI agents; it has more GitHub stars (213,329 vs 101,230).
  9. Claude Code (Paid): Anthropic's terminal coding agent that edits code, runs commands and handles git. Consider it because it is a managed commercial product, if you'd rather not run it yourself; it also covers terminal and CLI agents; it has more GitHub stars (150,707 vs 101,230).
  10. CC Switch (Open source): Desktop manager for Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw and other coding agents that switches API providers in one click and manages MCP servers, skills and prompts. Consider it because it is ready to use without building anything; it also covers computer and desktop control and MCP servers; it has more GitHub stars (145,685 vs 101,230).

Claude-Mem vs alternatives at a glance

ToolPricingOpen source / licenceGitHub starsGood for
Claude-MemOpen sourceApache License 2.0101,230writing code, memory for agents
Context ModeSource-availableElastic License 2.0 (source-available)30,192writing code, memory for agents
AgentMemoryOpen sourceApache License 2.029,593writing code, memory for agents
BeadsOpen sourceMIT27,943writing code, memory for agents
MiMo CodeOpen sourceMIT13,675writing code, coding in the terminal
LazyCodexOpen sourceYes3,792writing code, building AI agents
CompozyOpen sourceYes2,806writing code, coding in the terminal
DosuSee siteNo—writing code, memory for agents
opencodeOpen sourceMIT213,329writing code, coding in the terminal
Claude CodePaidProprietary (All rights reserved; Anthropic Commercial Terms of Service)150,707writing code, coding in the terminal
CC SwitchOpen sourceYes145,685writing code, coding in the terminal

More: Claude-Mem listing · All coding tools · All alternatives pages

Related searches: AI agent memory tools

Alternatives are picked from directory data only: same category plus shared tasks and sub-tasks. Pricing is as each maker states it; GitHub stars as recorded on each listing.

Get the best new AI agents, weekly

One short email with new tools, launches and what's worth trying. Free, unsubscribe anytime.