AIGS
ModelsRankingsDocsAgent
Sign inSign up

AIGS

Your AI token station — affordable, reliable, world-class AI fueling your work and life.

Quick links

  • API Console
  • Service Status
  • Pricing
  • AIGS Agent

Contact us

  • Email: support@aigs.cc
  • Terms of Service
  • Privacy Policy
  • Disclaimer

© 2026 AIGS. All rights reserved. · AI-generated content is for reference only. Please comply with local laws.

We use cookies to improve your experience, analyze site traffic and remember your preferences. By continuing to browse, you agree to our use of cookies.

Official terminal agent · Deeply bound to AIGS billing

Make every session faster, sharper, clearer

AIGS Agent is a terminal AI coding agent with a fully transparent per-request token ledger. Strong models for the main loop, sensible tiers for subtasks, and cache reuse that keeps long sessions efficient.

Per-request ledgerCost-aware routingCache optimizationDual protocol
Install nowIntegration guide
aigs — ~/my-project

$ aigs

main · ledger on · prompt cache on

> add email format validation to the login page

⚙ edit src/auth/login.tsx (+14 −2)

✓ lint · typecheck · test 12 passed

turn 3 · in 12,480 · cached 9,216 · 4.2s

Illustration: the main tier edits and verifies automatically, every turn lands in the ledger, context stays light

Capabilities

Built for speed, accuracy and transparency

Core differentiators: cost transparency + cost awareness — usage, prices and progress, all in plain sight

Per-request token ledger

Every request records usage, cache hits and cost — aggregated per turn, per session and per model, live in the status bar. Export a per-request CSV with /export cost and reconcile it line by line against the console usage page.

Cost-aware routing

Strong models for the main loop to protect quality; compaction, summarization and other subtasks automatically pick more economical tiers, with the ledger recording where every token went.

Cache-hit optimization

Explicit prompt-cache management at the protocol layer plus an append-only context design keep hit rates high — repeated content is reused instead of recomputed.

Smart compaction

Tool-result aging plus summary compaction. /compact with preview and undo keeps your context light without losing the plot.

Verification loop

After each change the agent runs lint / typecheck / test automatically and feeds failures back by file:line for up to three auto-fix rounds.

Permission guard

Readonly pass-through, bash allowlist with per-command approval, unconditional blocking of dangerous commands. Corporate proxies and self-signed certificates work out of the box.

Quick Start

Three steps to start

Already have an AIGS account? One minute to wire up your terminal

  1. 1

    Create an API key

    Sign in to the console, create and copy your key (starts with sk-) on the API Keys page.

    Open console →
  2. 2

    Install the agent

    One command to install globally (requires Node.js 18+ or Bun).

    npm i -g aigs-agent
  3. 3

    Configure and run

    Set the environment variable, then run aigs inside your project directory.

    export AIGS_API_KEY=sk-your-key
    aigs
Release notes

On Windows you can double-click start.cmd for a guided start; running from source also works (bun install && bun run dev).

Slash Commands

The commands you need, at your fingertips

Type / in a session to open the command palette — these are the high-frequency ones

/cost

Per-request ledger and summary of this session

/export cost

Export a per-request CSV to reconcile with the console

/model

Browse the live list and switch the main model

/model sync

Force a platform sync (listing / delisting / prices)

/compact

Compact context with preview and undo

/thinking

Tune thinking effort to balance speed and usage

/permission

Approval mode with a per-command bash allowlist

/doctor

Self-check network and config — first stop for debugging

Visibility & Control

Full visibility, spending under control

What you can see, you can control

Per-request detail

Model, token usage, latency and cost of every request are on the record; export a full CSV with /export cost.

Budget guards

Per-task turn and spend caps are configurable — the agent pauses at the limit with progress preserved, never out of control.

Platform reconciliation

The ledger reconciles line by line with the console usage page; prices sync with the platform automatically.

* Cache hits are billed at the platform cache price; rates vary by model — see the console for live pricing. Read the prompt caching billing guide

Cost-Aware

Three-tier routing, each tier does its job

Built-in three-tier routing; the model list syncs with the platform automatically — listing, delisting and price changes apply in near real time

Main tier

Complex tasks and code generation — quality first

Sub tier

Routine assistance — balanced

Cheap tier

Compaction, summaries, titles — cost first

Browse available models and live prices →

Also using opencode, Claude Code, Codex or other third-party clients?

See the Agent integration guides →

FAQ

FAQ

▸How is AIGS Agent different from opencode or Claude Code?

AIGS Agent is built by AIGS and deeply bound to the platform's billing system: model lists and prices sync automatically, the per-request ledger reconciles line by line with the console usage page, and it is purpose-built for efficiency with cost-aware routing and cache optimization. opencode and Claude Code are general third-party clients — AIGS provides integration guides for them too.

▸Are my key and code safe?

Your API key stays on your machine (~/.aigs/config.json) and is never sent to any third party. Tool calls go through permission guards and approvals; sensitive files are write-protected by default and dangerous commands are always blocked.

▸What happens when models or prices change?

The agent syncs the platform's live model list every 6 hours (listing, delisting and price changes apply automatically), and you can force a refresh anytime with /model sync. Delisted models are clearly flagged with guidance to switch.

▸Which model protocols are supported?

Built-in dual adapters for OpenAI and Anthropic: GLM, DeepSeek, Qwen and more via the OpenAI-compatible endpoint; the Claude family via the native /v1/messages entry with discounted cache billing — no third-party LLM SDK involved.

▸Which systems are supported?

It is a cross-platform CLI: macOS, Linux and Windows all work, requiring Node.js 18+ (recommended) or Bun. On Windows you can double-click start.cmd for a guided start.

▸What if my context gets too long?

Tool results age out automatically, and /compact does summary compaction — with preview to inspect the result, full for a deeper pass, and undo to roll it back in one step. Long sessions stay light.

Sign up and equip your terminal with a fast, transparent coding agent

Free credits on sign-up, one npm command, one minute to start

npm i -g aigs-agent

Register and install for freeIntegration guide

macOS / Linux / Windows · requires Node.js 18+ or Bun