ai-memory vs cortex-mem
Long-term memory for coding agents and AI applications
ai-memory preserves coding-agent activity in a self-hosted, git-backed Markdown wiki, while cortex-mem provides a memory framework for AI agents and applications. ai-memory emphasizes inspectable project records and handoffs that work without LLM calls; cortex-mem combines LLM-based memory extraction with semantic search and multiple access options.
ai-memory: Share Long-Term Memory Across Coding Agents
A self-hosted Rust service that captures coding-agent activity into a searchable, git-backed Markdown wiki and hands work between agents. It suits developers and teams who want portable project memory without requiring LLM calls.
cortex-mem: Give AI Agents Persistent Long-Term Memory
Cortex Memory is a Rust framework for storing, extracting, and searching long-term memories for AI agents and applications. It combines durable file-based storage with semantic search, and offers CLI, REST API, and MCP access.
| ai-memory | cortex-mem | |
|---|---|---|
| Language | Rust | Rust |
| License | MIT | MIT |
| Stars | 9.1k | 311 |
| Forks | 632 | 24 |
| Last analyzed | Oct 10, 2026 | Oct 3, 2026 |
Key differences
- ai-memory captures coding-agent sessions and supports typed handoffs, while cortex-mem extracts structured memories from conversations for reuse across sessions.
- ai-memory uses ordinary Markdown files as its source of truth with a derived retrieval index; cortex-mem stores Markdown in a virtual filesystem and pairs it with vector search.
- ai-memory's basic capture, search, and handoff path does not require an LLM provider; cortex-mem's extraction and embeddings depend on configured model services, and its full system requires Qdrant.
- ai-memory is aimed at developers and teams sharing project context across agents, machines, and contributors; cortex-mem targets developers building agents and personalized AI assistants.
- Both projects use Rust and have an MIT license; ai-memory has 8.8k stars and 608 forks, while cortex-mem has 311 stars and 24 forks.
Choose ai-memory if you…
- need coding-agent session capture and handoffs between agents or teammates.
- want project knowledge stored in inspectable, editable, git-backed Markdown files.
- prefer basic capture, search, and handoffs that do not require LLM API calls.
Choose cortex-mem if you…
- are building an AI agent or personalized assistant that needs conversation memory extraction.
- need layered memories, semantic search, and metadata filtering with Qdrant.
- want CLI, REST API, MCP, or Rust integration options, plus tenant-aware memory spaces.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.