Reliary

Grammar-free code intelligence and bash compression for AI coding agents.

A single Rust binary that indexes any codebase through structural detection — no tree-sitter, no AST, no per-language code — and exposes the index to agents over the Model Context Protocol (MCP). The companion command reliary wrap compresses verbose shell output (cargo test, git diff, pytest) before it reaches agent context.

What it is for. Answering "where is X defined", "who calls X", "what methods does X have" in one small tool call instead of a grep-then-read cycle. On the benchmark it answers at ~42% lower billed token cost than grep with about four times smaller tool output, at accuracy comparable to grep and clearly ahead of codebase-memory-mcp (the other MCP index tested).

Install

Prebuilt binaries for Linux (x86_64, aarch64), macOS (Intel, Apple Silicon), and Windows (x86_64, aarch64) are attached to every release. Download the archive for your platform from the latest release page, or:

# Linux x86_64. Substitute darwin/windows and aarch64 as needed.
VER=$(curl -s https://api.github.com/repos/Reliary/reliary-agent/releases/latest | grep -oP '"tag_name": "\K[^"]+')
curl -sSfL "https://github.com/Reliary/reliary-agent/releases/download/${VER}/reliary-agent-${VER}-linux-x86_64.tar.gz" | tar xz
./reliary-agent-${VER}-linux-x86_64 --version

Once installed, reliary update self-updates from the same releases with SHA-256 verification, and detects an existing cargo install and points you at the right upgrade command instead of clobbering it.

From source (needs a C compiler — the bundled SQLite and rustls build it):

cargo install reliary-agent

Quick start

# Index a project
reliary trust .

# Start the MCP server (Claude Code, OpenCode, Pi, Cline, anything MCP)
reliary mcp

Agent integration

reliary init detects installed agents and offers to wire itself in. To do it by hand:

Claude Code (~/.claude.json):

{
  "mcpServers": {
    "reliary": { "command": "/path/to/reliary", "args": ["mcp"] }
  }
}

OpenCode (~/.config/opencode/opencode.json; on macOS ~/Library/Application Support/opencode/opencode.json):

{
  "mcp": {
    "reliary": { "command": "/path/to/reliary", "args": ["mcp"] }
  }
}

Cline (cline_mcp_settings.json): same shape as the Claude entry.

Pi Agent: reliary init installs the Pi extension (gate.js), which routes tool calls through reliary.

Bash compression

Prefix a command with reliary wrap to compress its output:

reliary wrap cargo test    # collapses "Compiling" lines, keeps errors + summary
reliary wrap git diff      # drops context lines, keeps hunk headers + changes
reliary wrap pytest -v     # collapses passing lines to a summary

For automatic interception with no manual prefix, set RELIARY_SIFT_BASH=1 and install the hook from crates/reliary-agent/hooks/ for your agent.

Tools

The default MCP menu exposes six tools plus one verifier:

Every response ends with a freshness stamp [idx:xxxxxxxx] that changes only when the index changes.

CLI

reliary trust [PATH]         Index a project directory
reliary index [PATH]         Build or refresh the index
reliary reindex-file PATH    Re-index one file after an edit (used by hooks)
reliary search QUERY         BM25 search
reliary mcp                  Start the MCP server on stdio
reliary wrap [CMD]           Run CMD and compress its output
reliary sift [--stdin]       Pipe text through the compressor
reliary compress PATH        IR reasoning compression
reliary dead [PATH]          Cross-file dead-code analysis
reliary risk FILE            Pre-edit risk analysis
reliary impact SYMBOL        Blast radius: callers, test files, risk verdict
reliary test-plan            Which tests exercise the changed files/symbols
reliary diff REV REV         Structural diff between two revisions
reliary map                  Render a self-contained SVG map of the codebase
reliary verify TEXT          Verify a claim about the codebase
reliary fix TASK             Deterministic bug-fix recipes, LLM fallback
reliary bench                Generate benchmark questions+GT and score results
reliary init                 Auto-install agent integrations
reliary uninstall            Remove agent integrations
reliary doctor               Health check
reliary status               Index and integration status
reliary logs                 Tail the log output
reliary config               Show resolved configuration
reliary clean                Clean caches and state
reliary update               Self-update from GitHub releases (checksum-verified)
reliary completions SHELL    Emit a shell completion script
reliary man                  Emit the man page

Run reliary --help for the complete, current list.

Key properties

• Grammar-free: no tree-sitter, no AST, no per-language code. Structural detection on brace/indent/blank-line boundaries works on any text file.
• Index-first: once trusted, queries use the per-project SQLite index at .reliary/index.sqlite.
• Deterministic: identical inputs produce identical output, so results are safe for provider-side KV caching.
• Standalone: one Rust binary, no Python or Node runtime, no daemon.

Benchmarks

Measured with a deterministic claim-verification harness on a 10-question corpus, 4 seeds, deepseek-v4-flash. reliary's F1 leads the alternative MCP backend clearly and grep narrowly; the reliary-vs-grep gap is within noise on this single small corpus, so accuracy is presented as comparable to grep. The reproducible wins are cost, output size, and zero dead-ends.

Full methodology, the edit-outcome result (a tie — no demonstrated advantage), the familiarity experiment, and a zero-cost cassette replay are in docs/BENCHMARKS.md.

License

MIT