ai-memory vs plur
Persistent memory for coding agents compared
ai-memory and plur both help coding agents retain knowledge across sessions and tools. ai-memory centers on a self-hosted service and a git-backed Markdown wiki, while plur uses local YAML files and supports Git sync across devices or teams.
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.
plur: Share Persistent Memory Across AI Agents
PLUR gives AI agents a shared, local-first memory store of readable YAML files. It suits developers who want corrections and project conventions to carry across sessions and tools without relying on a hosted memory service.
| ai-memory | plur | |
|---|---|---|
| Language | Rust | TypeScript |
| License | MIT | Apache-2.0 |
| Stars | 9.1k | 298 |
| Forks | 632 | 36 |
| Last analyzed | Oct 10, 2026 | Oct 10, 2026 |
Key differences
- ai-memory captures prompts, tool calls, and session boundaries, then organizes observations into Markdown pages; plur stores engrams, corrections, conventions, and timestamped episodes in YAML.
- ai-memory offers full-text search, entities, links, and optional vector search; plur uses keyword and embedding-based retrieval, with keyword fallback when embeddings are unavailable.
- ai-memory is written in Rust and licensed under MIT; plur is written in TypeScript and licensed under Apache-2.0.
- ai-memory can run locally or as a shared server with multi-user authentication and audit logs; plur is local-first and supports sharing or sync through configured Git remotes.
- ai-memory provides typed, claim-once handoffs for unfinished work; plur focuses on saving and recalling memories, injecting them into agent context, and tuning retrieval with feedback.
- ai-memory notes that native Windows support is experimental and that integrations vary in status; plur advises checking specific integration needs given its open-issue backlog.
Choose ai-memory if you…
- want a self-hosted service with a git-backed Markdown source of truth.
- need typed handoffs between supported agents, along with capture of prompts and tool activity.
- want team sharing through a server with user attribution and an audit log.
Choose plur if you…
- prefer readable YAML memory files stored locally.
- want to sync selected memory across devices or teams using Git.
- need timestamped event episodes and retrieval that can fall back to keyword search when embeddings are unavailable.
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.