# HKUDS/FastCode

"FastCode: Accelerating and Streamlining Your Code Understanding"

Repository: https://github.com/HKUDS/FastCode
Canonical: https://ross.abutalabs.com/products/fastcode
Homepage: https://arxiv.org/abs/2603.01012
Language: Python
License Family: other
Last push: 2026-07-06T12:05:56+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 40, longevity 14
- inputs: {"age_days": 201, "days_push": 58, "days_rel": 189, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2292, forks 276 (observed 2026-08-28T04:06:34.945495+00:00)

## What it is
FastCode is a token-efficient framework for repository-scale code understanding and reasoning, using structural scouting over a semantic map of the codebase to build high-value context in a single optimized step. It claims to be faster and cheaper than Cursor and Claude Code, and ships as an MCP server for tools like Cursor, Claude Code, and Windsurf.

## Use cases
- understand a large codebase quickly
- answer questions about a repository with an LLM
- trace cross-repo dependencies
- reduce token costs when analyzing code with AI
- integrate code reasoning into Cursor or Claude Code via MCP
- debug complex codebases with AI assistance

## When to choose
- you need repository-scale code Q&A or reasoning with lower token cost
- you work with very large or multi-repo codebases
- you want an MCP server for code understanding in your AI IDE

## When to avoid
- you need a fully permissively licensed tool and license clarity matters (no license file is published)
- you need a mature production tool with long-term support
- your codebase is small enough that a plain LLM suffices

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, developer-tools, mcp
- domain: developer-tools, large-language-models, programming-languages
- platform: python, cli, cross-platform
- tags: code-understanding, repository-analysis, token-efficiency, code-reasoning, mcp-server, code-navigation, ai-agents

## Member repositories
- HKUDS/FastCode (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:34.945495+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:40:39.467916+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/FastCode (fetched 2026-08-28T04:06:34.945495+00:00, sha a970983c5b5e)
  - homepage: https://arxiv.org/abs/2603.01012 (fetched 2026-08-29T10:20:54.066779+00:00, sha 61351f7fb88e)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:20:54.076383+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:20:54.082465+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:20:54.084717+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:20:54.079833+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.