# freecodexyz/free-code

The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.

Repository: https://github.com/freecodexyz/free-code
Canonical: https://ross.abutalabs.com/products/free-code
Homepage: https://x.com/paoloanzn/status/2039022418698907949?s=20
Language: TypeScript
License Family: other
Last push: 2026-07-29T20:31:34+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 11
- inputs: {"age_days": 155, "days_push": 35, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8722, forks 2044 (observed 2026-08-28T04:10:24.436545+00:00)

## What it is
A community fork of Anthropic's Claude Code terminal AI coding agent, rebuilt from an exposed source snapshot with telemetry removed, security-prompt guardrails stripped, and experimental feature flags enabled. It ships as a single buildable TypeScript project installed via a one-line script and works with the user's preferred model provider.

## Use cases
- use an AI coding agent in the terminal without telemetry
- run Claude Code with experimental features unlocked
- self-build a de-telemetried Claude Code CLI
- code with an AI agent that doesn't phone home
- try experimental Claude Code feature flags early
- use Claude Code with a custom model provider

## When to choose
- you want a terminal-native AI coding agent with no telemetry or analytics
- you want to enable experimental Claude Code features that are gated upstream
- you prefer building from source and auditing what the agent sends over the network

## When to avoid
- you need official support, updates, or a license - the project has none
- you rely on upstream security guardrails and managed-settings enforcement
- your organization requires sanctioned, vendor-supported tooling
- you are uncomfortable using code derived from an unofficially exposed source snapshot

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, developer-tools, cli, prompt-engineering
- domain: developer-tools, large-language-models, privacy
- platform: cli, cross-platform, bun, windows
- tags: claude-code-fork, ai-coding-agent, telemetry-free, deguardrailed, terminal-agent, no-license, unofficial-fork, command-line, ai-agents, nodejs, macos, linux

## Member repositories
- freecodexyz/free-code (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:24.436545+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 2026-08-29T17:25:19.903050+00:00, confidence not recorded.
  - readme: https://github.com/freecodexyz/free-code (fetched 2026-08-28T04:10:24.436545+00:00, sha 098bda664aa4)
- Data as of 2026-08-30T08:39:29.467469+00:00.