Baike.dev
All toolsOnline toolsAI codingTrendingOpen sourceNewsSubmit
Log in
< Back to tools
G

gajae-code

> 编程语言
Open source

Gajae Code MVP

2.3K stars0 likes1 views
WebsiteGitHub

About

Gajae Code MVP

English | 한국어 | 中文 | 日本語

G A J A E - C O D E

Encode intention. Decode software.
The coding agent that runs on the plan you already pay for — and answers to your phone.

️ Explore Gajae-Code App → Desktop & self-hosted web GUI
Experimental, community-built third-party project — not an official first-party Gajae-Code app.

Quick Start · Why · Coding Plans · Phone · Workflow · Token Diet · Controllers · Agent Shells · Docs

Log in with the subscription you already have, plan before a single file mutates, execute with evidence — and answer the agent's questions from your terminal, your phone, or your own bot.

Gajae-Code (gjc) is an external coding-agent harness: drop it into any repository or worktree. No separate API billing. No per-token anxiety. No terminal babysitting.

Gajae-Code is an experimental, beta-stage project. Expect rough edges and verify outputs before relying on it for important work.


Why Gajae-Code?

Most coding agents fail on three fronts: they bill you twice, they mutate before they understand, and they go silent the moment you step away from the keyboard.

Problem What Happens Gajae-Code Fix
Separate API billing You pay for a plan and per-token API costs /login with the coding plan you already pay for — Claude, Codex, Cursor, Copilot, OpenCode Go, GOAT, ClinePass, and more
Code-first agents The agent edits before it understands; you rework Plan-gated workflow: interview → plan → critique → then mutate, with approval gates
Terminal-bound sessions Agent asks a question at 2 AM; work stalls until morning Questions route to Telegram/Discord/Slack; you answer from anywhere
Context bloat Whole-file reads and log floods burn the window Structural summaries, artifact spill, cache-aware routing, compaction

Quick Start

Install — prebuilt binaries for Linux (x64/arm64), macOS (arm64/x64), and Windows (x64). Bun is not required:

bash
curl -fsSL https://raw.githubusercontent.com/Yeachan-Heo/gajae-code/v0.15.3/scripts/install.sh -o gjc-install.sh
sh gjc-install.sh
gjc

Piping main executes mutable content; use it only if you explicitly want the latest installer:

bash
curl -fsSL https://raw.githubusercontent.com/Yeachan-Heo/gajae-code/main/scripts/install.sh | sh

Windows (PowerShell), tagged:

powershell
Invoke-WebRequest -UseBasicParsing https://raw.githubusercontent.com/Yeachan-Heo/gajae-code/v0.15.3/scripts/install.ps1 -OutFile gjc-install.ps1
powershell -File gjc-install.ps1

First use — pick your plan and go:

/login                       pick a provider / coding plan
/skill:deep-interview        clarify ambiguous requirements
/skill:ralplan               build and critique the plan
gjc ultragoal create-goals --brief-file <approved-plan>

Run modes:

bash
gjc                                # run in the current checkout
gjc --tmux                         # tmux-backed leader session
gjc --tmux --worktree my-task      # isolated worktree for risky work
gjc @screenshot.png "What should I change?"   # image input

Nightly channel: sh gjc-install.sh --channel nightly (use the tagged installer downloaded above). Full install matrix, Windows setup, update channels, and shell completion: docs/install.md. Bun is only needed to build from source.


Bring your coding plan

Log in once and run GJC on the subscription you already pay for. Run /login inside a session and pick your plan:

Plan / subscription OAuth login
Claude Pro / Max anthropic
ChatGPT Plus / Pro (Codex) openai-codex (browser) · openai-codex-device (headless)
Cursor cursor
GitHub Copilot github-copilot
OpenCode Zen / OpenCode Go opencode-zen · opencode-go
Kimi Code / Coding Plan / Moonshot kimi-code · moonshot
Z.AI GLM Coding Plan zai
MiniMax Coding Plan (Intl / CN) minimax-code · minimax-code-cn
xAI (Grok) xai
Alibaba Token Plan / Qwen Portal alibaba-token-plan · qwen-portal

More OAuth plans — Google Gemini CLI, GitLab Duo, Perplexity Pro/Max, Fire Pass, Xiaomi Token Plan — are covered in docs/models.md.

New: coding-plan presets

Key-based coding plans onboard with one command — the preset writes the API type, base URL, env var, compatibility flags, and a live model catalog together, so new models show up without a GJC update:

bash
gjc setup provider --preset commandcode-goat   # Command Code GOAT plan (CMD_API_KEY)
gjc setup provider --preset cline-pass         # ClinePass (CLINE_API_KEY)
  • Command Code GOAT — discovers the provider's live /provider/v1/models catalog and keeps every discovered model, including Claude-named IDs, on the provider's OpenAI-compatible /chat/completions transport. Login verifies entitlement with a fixed harmless inference probe before persisting credentials. Aliases: commandcode, goat.
  • ClinePass — no hardcoded models; GJC fetches Cline's live catalog the same way Cline generates its own. Aliases: clinepass, cline.
  • Also available as presets: minimax, minimax-cn, glm, alibaba-token-plan — or /provider add --preset <name> inside the TUI.
Beyond coding plans: 50+ providers, gateways, local runtimes

API-key providers, local runtimes (Ollama, LM Studio, vLLM), and gateways (Cloudflare AI Gateway, Vercel AI Gateway, LiteLLM, and more) all work. Register your own endpoints in models.yml, pool multiple accounts per provider with usage-aware routing, mix vendors per agent role with model presets and profiles, or centralize team credentials with the auth broker/gateway.

  • Models, providers, and auth resolution
  • Custom providers & multi-account routing
  • Multi-vendor role profiles
  • Auth broker & gateway (shared team credentials)

Answer from your phone

When the agent needs a decision, it pings you on Telegram — and you answer from anywhere:

  • Coordinator/lifecycle session forum topics with live/finalized output, context updates, image attachments, inline buttons, free-text replies, and typing indicators.
  • Configure once from /settings → Notifications in a running session, or headless via gjc notify setup|status|health|test|recovery. Tokens are masked on entry and never displayed again.
  • gjc daemon keeps one safe long-poll owner per bot token, so new sessions attach cleanly without Telegram 409 conflicts.
  • Discord and Slack delivery ship alongside; the generic action_needed/reply protocol lets any bot or mobile app route answers back without terminal scraping.

Telegram onboarding · Discord · Slack


Plan before mutation

A deliberately small workflow surface — four skills, four role agents, nothing else:

deep-interview -> ralplan -> ultragoal
               └─ optional autoresearch mission when research must ground the plan
Surface What it does
deep-interview Turns vague requests into concrete requirements.
ralplan Builds and critiques the implementation plan before code changes.
ultragoal Tracks goals through execution, revision, verification, and evidence.
autoresearch Runs goal-directed research missions and ends on a structured verdict.
executor / architect / planner / critic Bundled role agents for implementation and read-only review lanes.

Also included, opt-in: computer-use (experimental desktop control). See Python REPL and docs/tools/computer.md.

Custom skills

GJC uses the Claude Code / Codex SKILL.md file convention, but loads runtime skills directly only from canonical GJC locations — no configuration required:

bash
# project-local, per repository:
mkdir -p .gjc/skills && cp -r my-skill .gjc/skills/

# user-wide, available in every project:
mkdir -p ~/.gjc/agent/skills && cp -r my-skill ~/.gjc/agent/skills/

Claude Code and Codex skill directories are import sources only. gjc skills discover reports them with the exact copy command; copy a skill into a canonical .gjc location before invoking it with /skill:my-skill. Scope trust is explicit via skills.trustProjectSkills / skills.trustUserSkills (both default on), with skills.enabled as the master switch. The four bundled workflow skills above can never be replaced by disk skills. See docs/skills.md for locations, precedence, and diagnostics.

Theme defaults

The default dark TUI identity is the GJC red-claw theme; light-appearance terminals default to the bundled blue-crab theme. Explicit theme settings still take precedence.


Spend fewer tokens

GJC optimizes both sides of the token bill:

  • Cache hits — per-provider cacheRetention control; Anthropic defaults to long (1h) cache retention because short caches are fragile for long agent runs; provider ranking prefers cheap cacheRead paths; opt-in session-affinity headers let OpenAI-compatible relays reuse server-side prompt caches.
  • Context savings — file reads return structural summaries instead of whole files; oversized shell output is minimized and spilled to retrievable artifact:// references instead of flooding the context; compaction and branch summaries keep long sessions inside the window without losing prior work.

Cache retention & provider compat · Compaction & branch summaries


The default dark TUI identity is the GJC red-claw theme; light-appearance terminals default to the bundled blue-crab theme. See docs/theme.md for the full catalog and theme.dark / theme.light settings.

Let OpenClaw / Hermes / Grokbot / your own bot drive GJC

Any external controller — OpenClaw, Hermes, Grokbot, a Discord bot, a cron script — drives real GJC sessions through the broker-bound SDK session CLI and the bundled sdk-skills/ procedures (gjc-sdk-discover · gjc-sdk-operate · gjc-sdk-author). Durable turns and credential-free JSON, never terminal scraping.

Don't read a guide — paste this prompt into your controller and let it wire itself up:

Copy-paste controller setup prompt
…

Long prompts are safe to leave running: the SDK prompt deadline is a progress-aware inactivity lease (sdk.promptDeadlineMs, 30 min default) bounded by sdk.promptMaxRuntimeMs (6 h default), renewed only by attributable tool execution for the accepted turn — not by heartbeats or streaming text.

Need event-

Issues· 0 open

View all issuesOpen on GitHub

No open issues yet, or sync has not completed.

> Tags

TypeScript

No comments yet. Be the first to share.

> Details

PublishedAug 1, 2026
UpdatedSep 17, 2026
Category编程语言
PricingOpen source

> Related tools

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言