// mesrai · docsai code review · free for individuals
AI code review that understands your architecture.
Multi-agent reviewer reads your repo as a graph — not just the diff. Catches bugs, security risks, and design issues on every PR, with rules you write and the model you pick.
// explore the docs
Pick where you want to start
Quickstart
Connect a repo and see your first AI review in minutes.
How code review works
Multi-agent flow over an AST graph of your repo.
Mesrai Rules
Plain-English or YAML rules. Apply per-org, per-repo, per-directory.
BYOK
Bring your own OpenAI, Anthropic, Vertex, Bedrock, or any compatible key.
Pricing
Free ₹0, Pro ₹999 AI Included / ₹499 BYOK, Enterprise custom.
CLI
Run Mesrai reviews from your terminal or CI agent.
// bring your own model
Works with any LLM provider
Mesrai is provider-agnostic. Plug in OpenAI or Anthropic for the default catalog, or wire any OpenAI-compatible endpoint. Token bills land on your provider — Mesrai never adds margin.
Z.ai
GLM-4.6 + reasoning models from Zhipu.
Groq
Ultra-fast inference on Llama 3, Mixtral, and more.
Together AI
Open-source models at competitive prices.
Fireworks
Production-grade hosted open models.
Moonshot
Kimi models with long-context support.
Novita
Serverless GPU inference platform.
Chutes
Frontier models on shared infrastructure.
Synthetic
Specialized inference endpoints.
Also supported: OpenAI · Anthropic · Vertex · Bedrock · Ollama · vLLM · any OpenAI-compatible endpoint. See the BYOK guide.
Start reviewing with Mesrai
Free forever for individuals. INR billing + GST invoices on Pro and Enterprise.