huangzhenpc
2b29616723
Old format had 9+ lines per request with key=value noise, and concurrent requests interleaved without any way to tell which line belongs to which call. The new format: - Each line starts with the status code/outcome (200, 400, 429, FAIL, TIMEOUT, ERR) so success/failure is visible at a glance. - Every request gets a 6-char hex req_id; all lines for that request share it, disambiguating interleaved concurrent traffic. - Endpoint abbreviated to 2 chars (CW/Q), model stripped of "claude-" prefix, attempt compacted to "a1"/"a2". - Successful requests collapse to 2 lines (REQ start + 200 done with first_byte and total elapsed). Retries/errors add one line each. - Durations use fmtMs: <1s -> "235ms", >=1s -> "2.8s" (one sig fig). Sample successful request: [KiroAPI] REQ a3f2b1 model=opus-4.7 account=x@y endpoints=CW,Q [KiroAPI] 200 a3f2b1 CW/a1 first_byte=1.2s total=2.8s Sample fallback chain: [KiroAPI] REQ b8e3c4 model=opus-4.6 account=x@y endpoints=Q,CW [KiroAPI] 400 b8e3c4 Q /a1 INVALID_MODEL_ID 325ms retry 1/3 [KiroAPI] 400 b8e3c4 Q /a2 INVALID_MODEL_ID 242ms retry 2/3 [KiroAPI] 400 b8e3c4 Q /a4 INVALID_MODEL_ID 216ms exhausted -> fallback [KiroAPI] 400 b8e3c4 CW/a1 INVALID_MODEL_ID 452ms retry 1/3 ... [KiroAPI] FAIL b8e3c4 all endpoints failed 2.1s last=400
Kiro-Go
Convert Kiro accounts to OpenAI / Anthropic compatible API service.
If this project helps you, a Star would mean a lot.
Features
- Anthropic
/v1/messages& OpenAI/v1/chat/completions - Multi-account pool with round-robin load balancing
- Auto token refresh, SSE streaming, Web admin panel
- Multiple auth: AWS Builder ID, IAM Identity Center (Enterprise SSO), SSO Token, local cache, credentials JSON
- Usage tracking, account import/export, i18n (CN / EN)
- Support configuring outbound proxy (SOCKS5 / HTTP)
Quick Start
Docker Compose (Recommended)
git clone https://github.com/Quorinex/Kiro-Go.git
cd Kiro-Go
mkdir -p data
docker-compose up -d
Docker Run
docker run -d \
--name kiro-go \
-p 8080:8080 \
-e ADMIN_PASSWORD=your_secure_password \
-v /path/to/data:/app/data \
--restart unless-stopped \
ghcr.io/quorinex/kiro-go:latest
Build from Source
git clone https://github.com/Quorinex/Kiro-Go.git
cd Kiro-Go
go build -o kiro-go .
./kiro-go
Config is auto-created at data/config.json. Mount /app/data for persistence. The default admin password is changeme — override it via the ADMIN_PASSWORD env var or change it in the admin panel before going to production.
Usage
Open http://localhost:8080/admin, log in, add accounts, then call the API:
# Claude
curl http://localhost:8080/v1/messages \
-H "Content-Type: application/json" \
-H "anthropic-version: 2023-06-01" \
-d '{"model":"claude-sonnet-4.5","max_tokens":1024,"messages":[{"role":"user","content":"Hello!"}]}'
# OpenAI
curl http://localhost:8080/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer any" \
-d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello!"}]}'
Thinking Mode
Append a suffix (default -thinking) to the model name, e.g. claude-sonnet-4.5-thinking. Claude-compatible requests that include a top-level thinking config such as {"type":"enabled","budget_tokens":2048} or {"type":"adaptive"} also enable thinking mode automatically. Configure output format in the admin panel under Settings - Thinking Mode.
Outbound Proxy
For users in restricted network regions, configure an outbound proxy in the admin panel under Settings - Outbound Proxy Settings. Supports SOCKS5 and HTTP proxies.
The setting takes effect immediately without restarting.
Environment Variables
| Variable | Description | Default |
|---|---|---|
CONFIG_PATH |
Config file path | data/config.json |
ADMIN_PASSWORD |
Admin panel password (overrides config) | - |
Contributing
Friendly discussion is welcome. If you run into issues, try asking Claude Code, Codex, or similar tools for help first — most problems can be solved that way. PRs are even better.
Friend Links
Disclaimer
For educational and research purposes only. Not affiliated with Amazon, AWS, or Kiro. Users are responsible for complying with applicable terms of service and laws. Use at your own risk.