# Yeachan-Heo/gajae-code

Gajae Code MVP

Repository: https://github.com/Yeachan-Heo/gajae-code
Canonical: https://ross.abutalabs.com/products/gajae-code
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-26T21:53:32+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 7
- inputs: {"age_days": 99, "days_push": 7, "days_rel": 7, "gap_med": 0, "n_releases_24m": 96}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2618, forks 363 (observed 2026-08-28T04:07:04.623920+00:00)

## What it is
Gajae-Code (gjc) is an external coding-agent harness that runs AI coding agents in any repository using the coding subscription plans you already pay for (Claude, Codex, Cursor, Copilot, etc.). It enforces a plan-gated workflow (interview, plan, critique, then mutate) and routes agent questions to Telegram, Discord, or Slack so you can respond away from the terminal.

## Use cases
- run an AI coding agent without paying per-token API costs
- make a coding agent plan and get approval before editing files
- answer coding agent questions from my phone via Telegram or Discord
- drop an autonomous coding agent into an existing repo or worktree
- reduce context window bloat when using coding agents
- drive a coding agent from my own Discord or Telegram bot
- use my existing Claude or Copilot subscription for AI coding

## When to choose
- you already pay for a coding subscription and want to avoid separate API billing
- you want a plan-before-mutation workflow with approval gates
- you need to supervise and answer agent questions remotely from messaging apps
- you want a terminal/TUI coding agent harness you can drop into any repo

## When to avoid
- you need a production-grade, fully stable tool for critical work
- you prefer fully local or self-hosted model inference
- you want a GUI or IDE-integrated coding assistant rather than a CLI/TUI harness
- you need guaranteed token costs or SLAs from the vendor

## Facets
- artifact type: cli-tool
- maturity: experimental
- function: agent-framework, llm-inference, cli, developer-tools, prompt-engineering
- domain: developer-tools, artificial-intelligence
- platform: cli, cross-platform, windows
- tags: coding-agent, ai-agent-harness, terminal-ui, telegram, discord, slack, plan-gated-workflow, subscription-auth, tui, beta, ai-agents, command-line, automation, nodejs, macos, linux

## Member repositories
- Yeachan-Heo/gajae-code (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:04.623920+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 2026-08-30T02:20:16.806245+00:00, confidence not recorded.
  - readme: https://github.com/Yeachan-Heo/gajae-code (fetched 2026-08-28T04:07:04.623920+00:00, sha 9742a1be43ce)
  - registry_npm: https://registry.npmjs.org/gajae-code (fetched 2026-08-29T10:03:27.438711+00:00, sha c34f9681c157)
- Data as of 2026-08-30T08:39:29.467469+00:00.