Wadah Engine

Wadah

Where agents live and remember.

Wadah indexes your Git repository per commit (symbols, imports and structural changes) and serves that knowledge to AI coding assistants through a local MCP server. It runs entirely on your machine. When Wadah cannot analyze something, it says so instead of returning an empty result.

Wadah also packages and runs AI agents the way Docker packages apps (.wpkg packages, OCI push/pull, execution traces). That part is experimental; see Status.

Install

Prebuilt binaries for macOS (Apple Silicon and Intel), Linux (x64 and arm64) and Windows (x64) are attached to every GitHub Release, with SHA-256 checksums.

# macOS and Linux
curl -fsSL https://wadah.tech/install.sh | sh

# Homebrew
brew install techwadah-web/tap/wadah

# From crates.io (Rust stable)
cargo install wadah-cli

# Windows (PowerShell)
irm https://wadah.tech/install.ps1 | iex

Every method installs the wadah command. Check it with wadah --version. git is required; python3 and go are optional and enable the Python and Go adapters (without them those files are reported as unsupported, never as empty).

To build from source instead:

git clone https://github.com/techwadah-web/wadah-engine
cd wadah-engine
cargo install --path crates/cli --locked

Quick start

cd your-repo
wadah doctor             # check repository and knowledge-store readiness
wadah analyze            # analyze HEAD into a deterministic snapshot
wadah learn              # store it in the local knowledge store
wadah query "UserService"

Connect it to an MCP client such as Claude Code:

claude mcp add wadah -- wadah mcp serve --path .

The MCP server is read-only by default. Tools that write to the local knowledge store are only exposed when you pass --write.

Run wadah --help or wadah <command> --help for every command and option. Most commands accept --json or --plain for scripting and CI.

What you get

• Commit-pinned knowledge: snapshots of a repository at a given commit.
• Deltas and comparison: what changed between two commits or two repositories.
• Portable knowledge bundles: export and import with atomic, recoverable imports.
• MCP server: lets assistants query the knowledge store locally.
• Terminal UI and structured output for scripts.
• Agent packaging and runtime (experimental): .wpkg, OCI push/pull, traces.

Status

Area	Status
Knowledge store, delta, compare, query	Stable
Symbol analysis, MCP server, terminal UI, JSON output	Beta
Agent packaging (.wpkg, OCI push/pull)	Preview
Agent runtime (single model call), traces	Experimental
Policy / ToolCaps enforcement	Not enforced yet

• Stable: formats and commands change only with migration notes.
• Beta: works, but the API may change between minor versions.
• Preview / Experimental: try it, do not rely on it in production.
• Not enforced / Not functional: the code exists, the feature does not work as named yet.

See ROADMAP.md for what is planned next.

Privacy

Knowledge and MCP features run on your machine. No code is sent anywhere by Wadah itself.

Documentation

Start at docs/INDEX.md.

Contributing

Issues and pull requests are welcome. Read CONTRIBUTING.md and our Code of Conduct first. To report a security issue, see SECURITY.md.

License

Apache-2.0. See LICENSE and NOTICE.