ai-memory vs lat.md
Markdown knowledge tools for coding agents compared
ai-memory captures coding-agent activity in a self-hosted, git-backed Markdown wiki, with search and handoffs across agents, machines, and teammates. lat.md is a repository-based knowledge graph that links Markdown documentation to code; it focuses on validating and navigating project context within a development workflow.

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.

lat.md: Build a Markdown Knowledge Graph for Your Codebase
lat.md is a TypeScript CLI for maintaining a codebase knowledge graph in interconnected Markdown files. It links design notes and test specifications to source code, with validation and search to help developers and coding agents keep project context usable and in sync.
| ai-memory | lat.md | |
|---|---|---|
| Language | Rust | TypeScript |
| License | MIT | MIT |
| Stars | 9.1k | 2k |
| Forks | 632 | 126 |
| Last analyzed | Oct 10, 2026 | Nov 6, 2026 |
Key differences
- ai-memory records prompts, tool calls, and session boundaries, while lat.md organizes curated knowledge as linked Markdown sections connected to code.
- ai-memory supports typed handoffs and shared project memory across machines and teammates; lat.md emphasizes documentation links, code references, and graph validation.
- ai-memory is a Rust server and CLI that users self-host; lat.md is a TypeScript CLI and toolset maintained in the project repository.
- ai-memory's basic capture, search, and handoff path works without LLM API calls, with vector search optional; lat.md uses a bundled local embedding model for semantic search by default.
- Both projects use the MIT license. ai-memory lists 8.8k stars and 608 forks, while lat.md lists 2k stars and 122 forks.
Choose ai-memory if you…
- need to preserve coding-agent sessions and hand work off between agents or teammates.
- want a self-hosted, git-backed record of project activity that can be inspected and edited as Markdown.
- need basic capture, search, and handoffs without configuring an LLM provider.
Choose lat.md if you…
- want linked project documentation that connects concepts and decisions to code symbols and source files.
- need CLI checks for graph references or required code mentions.
- want semantic search and prompt reference expansion as part of a repository-based documentation workflow.
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.