PLUR is a local-first shared-memory engine for AI coding agents: one store of plain-text YAML "engrams" at ~/.plur/ that every wired harness on the machine reads and writes through an MCP server and per-harness adapter plugins. **Its bet is that memory should be shared across tools and owned as files: learn a correction in Claude Code, get it injected in Codex the same evening, and edit or delete the record in a text editor, because "the model is rented; your memory is owned."** ## What it is Open-source Apache-2.0 TypeScript packages from plur-ai (@plur-ai/core, @plur-ai/cli, @plur-ai/mcp on npm) that store each memory as a typed YAML assertion validated against a published JSON Schema, with activation decay, hierarchical scopes, do/don't polarity, and associations. Adapters (hooks plus plugins, not just tools) auto-inject memory for Claude Code, Codex, Cursor, OpenCode, OpenClaw, Hermes, Antigravity CLI, and DeepSeek Harness, while other MCP clients such as Windsurf and Gemini CLI get tools only; a Python SDK bridges LangChain and scripts to the same store. Recall is fully local hybrid search (BM25 plus BGE embeddings plus reciprocal rank fusion) with a BM25 fallback when the embedder is slow, and a `plur dashboard` command serves a read-only loopback viewer in English and Chinese. Sync is git over your own remotes, with scope-filtered pushes (shared remotes never receive personal or private engrams), and a PLUR Enterprise tier for team scopes is referenced without published prices. ## Status **Active and shipping, young, with self-published benchmarks and no independent coverage yet.** 304 stars, 37 forks, created 2026-03-19, pushed 2026-10-07, Apache-2.0, as of 2026-10-14 (GitHub API). Star History Chart @plur-ai/core is at 0.21.5, published 2026-10-07 (first publish 2026-03-22, npm registry), and the project was listed in awesome-claude-code on 2026-10-13. Its headline benchmark claims (full LongMemEval-S recall at 97.6 percent with a reranker, and Haiku with PLUR beating Opus without it at roughly ten times less cost) are self-published, with the harness public at plur-ai/plur-bench, a pinned corpus, and reproduction explicitly invited, but I found no independent reproduction or coverage of the project as of 2026-10-14. ## Strengths - One shared store across harnesses is the actual product, not a side effect: scope tags and per-engram scoping keep project knowledge from leaking into other projects. - Memory is plain YAML against an open, versioned spec, so it diffs in git, survives the engine, and can be corrected by hand. - The benchmark harness is published and reproducible with the corpus pinned and CI-checked, which is rare among memory vendors and better than a bare claims table. - Auto-injection adapters for eight harnesses attack the actual failure mode of tools-only memory, which is the model not choosing to call the tool under context pressure. ## Cautions - The marketing-forward claims rest on self-run numbers; "Haiku plus PLUR beats Opus" is a vendor benchmark until someone else runs plur-bench. - 0.x versioning on a six-month-old store format means schema churn is likely, and the adapters write into editor configs that `plur init` owns. - The Codex adapter needs a manual hook-trust step that fails silently (zero exit code, no warning) until done, a support trap the README itself documents. - The Enterprise tier is referenced with no public price, so the team-store path is a sales conversation, not a plan page. ## Pricing Free and open under Apache-2.0, with local search making zero API calls and costing nothing per query. A PLUR Enterprise tier for team scopes and remote team stores is referenced with no public price found as of 2026-10-14. ## Compared to [claude-mem](../claude-mem/index.md) runs the same capture-and-reinject job on SQLite with a hundred times the adoption and deeper Claude Code integration; choose PLUR when one store must serve several harnesses rather than one plugin serving one deeply. [Basic Memory](../basic-memory/index.md) is the other file-rooted memory, a markdown knowledge base the agent grows over MCP without auto-injection hooks; choose PLUR when capture should be automatic and recall tuned by feedback rather than curated by hand. [Zep](../zep/index.md) is the opposite pole, a hosted multi-user engine with bi-temporal validity and provenance; choose Zep when memory must serve users server-side and survive audit, not when one developer owns the store. ## Bottom line Recommended for a developer running several coding agents on one machine who wants one correctable, inspectable memory behind all of them. Not for multi-user products needing server-side per-user isolation, and not for anyone who requires independently verified benchmark numbers before adopting a dependency. ## Changes - 2026-10-14 - Created. ## See also - [claude-mem](../claude-mem/index.md) - the adoption leader of the same capture-and-reinject kind, SQLite where PLUR is YAML - [Basic Memory](../basic-memory/index.md) - the file-rooted MCP knowledge graph that shares PLUR's ownership thesis without its auto-injection - [Engrim](../engrim/index.md) - the other local-first cross-CLI store, provenance-first on one SQLite file - [Memory Feature Matrix](../memory-feature-matrix/index.md) - the shared-feature comparison PLUR now sits in - [Context Management Patterns](../../context-management-patterns/index.md) - the broader context techniques memory injection competes with ## References - https://github.com/plur-ai/plur - the repository: Apache-2.0 license, adapter matrix, 304 stars as of 2026-10-14 - https://raw.githubusercontent.com/plur-ai/plur/main/README.md - architecture, the harness support table, engram model, and sync semantics - https://plur.ai/spec.html - the engram spec: typed assertions, activation model, scopes, and the published JSON Schema - https://plur.ai/benchmark.html - the benchmark methodology behind the recall and cost claims - https://github.com/plur-ai/plur-bench - the reproducible benchmark harness with the pinned corpus - https://registry.npmjs.org/@plur-ai/core - publish history: 0.21.5 on 2026-10-07, first publish 2026-03-22 - https://github.com/hesreallyhim/awesome-claude-code - the listing that surfaced this note (PLUR added 2026-10-13)