Reference docs for the AI API and the Compute API, plus CLI tools and migration guides.
OpenAI-compatible API reference — retries, fallback routing, streaming, embeddings, request tracking.
Run jobs and serve models — badgr run, badgr serve, batch inference, fine-tuning, and more.
Use Badgr as the execution cloud behind your own AI product — agent, GPU, and model-serving use cases.
Free, open-source, local-first CLIs and libraries. Each installs from npm and runs without signup.
badgr-auto
local AI proxy that cuts token and routing costs
badgr-cli
run GPU jobs and serve models from one command
badgr-agent
CI pipeline check runtime for build failure triage
badgr-mcp
MCP server for provisioning GPU jobs from coding agents
badgr-agent-resume
resumable step checkpoints for agent runs
badgr-llm-guard
guarded AI API client with retries and spend caps
badgr-gpu-doctor
GPU VRAM and CUDA preflight checks
badgr-mcp-doctor
MCP server connection and tool diagnostics
badgr-config-doctor
env and config preflight checks
badgr-ci-triage
CI log failure triage and next-step suggestions
badgr-eval-check
repeatable assertions on LLM output
badgr-security-scan
offline secret and prompt-injection scanner
gpu-price-finder
compare live GPU pricing routes from the terminal
gpu-monitor
flag idle GPUs and estimate wasted spend
ai-prod-guard
production guard for AI apps: cost limits, retries, fallbacks