flash-context

A lightweight, model-agnostic repository explorer for AI agents, available as a Python CLI and Model Context Protocol (MCP) server. It combines deterministic lookup with search and reading delegated to a utility model through an OpenAI-compatible endpoint, returning compact, validated file-line citations and source snippets.

CLI and MCP share a read-only core for exploring code, documentation, configuration, and other local text files with path safety and resource limits. See safety and evidence validation for details and limitations.

Inspired by FastContext, a now-withdrawn paper on separating repository exploration from task solving, using specialized models to return focused file-line evidence while reducing the coding agent's context and token overhead.

Quickstart

Requires Python 3.13+, uv, and an OpenAI-compatible model endpoint with tool calling support.

uv tool install flash-context
export FLASH_CONTEXT_BASE_URL=http://localhost:1234/v1
export FLASH_CONTEXT_MODEL=your-model

flash-context explore --repo . --query "Find the request validation logic"

Replace the endpoint and model with your settings. Set FLASH_CONTEXT_API_KEY if authentication is required. Installed commands use environment variables; source checkouts also support project-root config.yaml and .env.

Default output is repository-relative citations:

src/api/validation.py:42-88

Use --no-citation for prose, --format json for results with snippets, or --max-turns 6 to set the exploration limit. Exact path and unique symbol lookups can resolve locally without an endpoint. See the CLI contract for options, output schemas, and exit codes.

For example, --query 'httpx/_client.py' returns a bounded file preview, while --query 'BaseTransport' returns its definition if unique within a complete Python source/stub scan. Local successes report turns_used: 0 in JSON.

Warnings go to stderr in both output formats. An empty result after scan-budget exhaustion exits 6 while preserving stdout; a complete empty search exits 0. For large repositories, see scan-budget tuning.

Models select symbol or line anchors; the controller resolves bounded syntax regions and returns structural precision metadata. See the shared contract for evidence rules and limits.

MCP

uvx --from 'flash-context[mcp]' flash-context mcp --transport stdio

Exposes explore_repository(query, repo_root?, max_turns?, citation?). See MCP integration for editor configuration and source launches.

Documentation

• Configuration: endpoint settings, precedence, and limits.
• Architecture and scope: shared core and module responsibilities.
• Contributing: development setup, tests, and pull requests.
• Changelog: release history and migration instructions.
• Releasing: package checks and tag-driven TestPyPI/PyPI publishing.

License

Apache License 2.0.