YAMS — Yet Another Memory System

Persistent memory for LLMs and apps. Content-addressed storage with dedupe, compression, full-text and vector search.

[!WARNING] Experimental — not production ready. Expect bugs and breaking changes until 1.0.

Features

• SHA-256 content-addressed storage with block-level dedupe (Rabin chunking)
• Full-text search (SQLite FTS5) + semantic vector search (embeddings)
• Tree-sitter symbol extraction for 18 languages (list)
• Snapshot management with Merkle tree diffs and rename detection
• WAL-backed durability, high-throughput I/O, thread-safe
• CLI, MCP server, and C-ABI plugins (ONNX/GLiNER/ColBERT, S3 storage, PDF via ZYP)
• Interactive relevance tuning through CLI tuning and doctor workflows

Documentation

Topic	Link
Install	docs/user_guide/installation.md
CLI reference	docs/user_guide/cli.md
MCP server	docs/user_guide/mcp.md
Embeddings	docs/user_guide/embeddings.md
Plugins	docs/PLUGINS.md
Build from source	docs/BUILD.md
Architecture	docs/architecture/
Benchmarks	docs/benchmarks/README.md
Changelog	docs/changelogs/
Roadmap	docs/roadmap.md

Links

• SourceHut: https://sr.ht/~trvon/yams/
• GitHub mirror: https://github.com/trvon/yams
• Docs site: https://yamsmemory.ai
• Discord: https://discord.gg/rTBmRHdTEc
• License: GPL-3.0-or-later

Install

Supported: Linux x86_64/ARM64, macOS x86_64/ARM64, Windows x86_64.

# macOS
brew install trvon/yams/yams

# Docker
docker pull ghcr.io/trvon/yams:latest

# Debian/Ubuntu, Fedora/RHEL, Windows: see installation guide

Full install matrix and package repos: docs/user_guide/installation.md.

Build from source

./setup.sh Release          # Linux/macOS (auto-detects toolchain, runs Conan + Meson)
meson compile -C build/release

./setup.ps1 Release         # Windows
meson compile -C build/release

Requires a C++20 toolchain (GCC 13+, Clang 16+, or MSVC 2022+ recommended), Meson, Ninja, CMake, pkg-config, and Conan. See docs/BUILD.md.

Quick Start

yams init                                # interactive; use --auto for headless
yams add ./README.md --tags docs
yams add src/ --recursive --include="*.cpp,*.h" --tags code

yams search "config file" --limit 5
yams grep "TODO" --include="*.cpp"

yams list --limit 20
yams get <hash> -o ./output.bin

Shell completions: yams completion bash|zsh|fish|powershell. Install instructions: docs/user_guide/cli.md#cmd-completion.

MCP Server

YAMS ships an MCP server over stdio (JSON-RPC) for AI assistants.

yams serve

{
  "mcpServers": {
    "yams": { "command": "yams", "args": ["serve"] }
  }
}

Tool reference and MCP client setup: docs/user_guide/mcp.md.

Plugins

yams plugin list                                  # loaded plugins
yams plugin trust add ~/.local/lib/yams/plugins   # trust a directory
yams plugin health                                # status
yams doctor plugin onnx                           # diagnose

Plugin architecture, trust model, and bundled plugins (ONNX, S3, ZYP, GLiNER, symbol extractor): docs/PLUGINS.md.

GPU acceleration (ONNX)

Platform	Provider	Hardware
macOS	CoreML	Apple Silicon Neural Engine + GPU
Linux	CUDA	NVIDIA GPUs
Linux	MIGraphX	AMD GPUs (ROCm)
Windows	DirectML	Any DirectX 12 GPU (NVIDIA, AMD, Intel)

Auto-detected at build. Override with YAMS_ONNX_GPU=auto|cuda|coreml|directml|migraphx|none. Details: plugins/onnx/README.md.

Simeon backend

YAMS uses simeon by default for both dense vector embeddings and lexical (BM25) search — no model download required. Set embeddings.backend = "simeon" in your TOML config (or leave it unset; simeon is the default). Fine-grained knobs live under [embeddings.simeon].

Simeon research now points to a practical ceiling-closing path for YAMS: pair retrieval with corpus adapters that expose structure the generic vector backend cannot infer alone — file paths, titles, sections, headings, issue IDs, citations, or domain-specific anchors. English ArguAna experiments moved from ~0.32 nDCG@10 with BM25 to ~0.76 with a topic adapter, while schema diagnostics showed the remaining headroom is structure recognition rather than more vector similarity.

YAMS now exposes this as a first-class search component: implement yams::search::CorpusAdapter, register it with SearchEngine::addCorpusAdapter(), or rely on the built-in YamsNativeCorpusAdapter for path-fragment and agent-memory metadata queries such as pbi=PBI-043 task=list-json-refresh. The native adapter uses English-first query seeding: it breaks natural-language requests into compact content/path fragments, keeps structured tokens such as docs/research or PBI-043, and records adapter_us, seed_count, and path_seed_queries in debug metadata for profiling. The component is enabled by default with SearchEngineConfig::enableCorpusAdapters and fused as corpus_adapter evidence.

PRs are welcome for qrel-backed English corpora, yams-specific corpus adapters, and language/profile contributions that make this retrieval path testable beyond the current research fixture.

Full config reference and dim tradeoffs: docs/user_guide/embeddings.md.

Troubleshooting

yams doctor              # full diagnostics
yams stats --verbose     # storage statistics
yams repair --all        # repair common issues

Build issues: docs/BUILD.md. Empty yams plugin list? Add a trust path: yams plugin trust add ~/.local/lib/yams/plugins.

Cite

@misc{yams,
  author = {Trevon Williams},
  title = {YAMS: Content-addressable storage with semantic search},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/trvon/yams}
}