For Indian law firms & in-house legal teams

Your firm's AI, trained on your firm's contracts.

Drop your past contracts, playbooks, and house rules into Orchestra. We distil your terminology, risk tolerances, and drafting style — then every agent run inherits them. Reviews and drafts come back in your firm's voice, against your jurisdiction, on the LLM your InfoSec team approves.

Free for design partners · no credit card · we ship your firm's data isolation by Postgres RLS, not by promise.

Upload
.pdf · .docx · .zip
Train
Map-reduce firm DNA
Draft
In your template
Why Orchestra

What other legal AI tools won't do

We're built for firms that need their AI to reflect their own style, run on their own infrastructure, and produce an audit trail that survives a real review.

Trained on YOUR docs

Drop your past NDAs, MSAs, employment agreements. We extract the firm's terminology, hard limits, and drafting style — and inject them into every agent's prompt. No prompt engineering, no copy-paste.

Bring your own LLM

OpenRouter is the default — swap to Anthropic, OpenAI, Gemini, or Azure OpenAI by changing one row. Your API key is encrypted at rest and only decrypted at call time. InfoSec-friendly by design.

Audit-grade by default

Postgres Row-Level Security on every tenant table. Every inference, tool call, pause, and resume lands in an append-only forensic log with a monotonic step number. Built for the next RBI / DPDPA review.

Self-hostable, open architecture

A single docker compose runs the whole stack. Exposes MCP so any agentic client (Claude Desktop, M365 Copilot) can plug in. Your data, your servers, your tokens — your choice.

How it works

Live in an afternoon

Sign up, drop a zip, train. By tea time the agents speak in your firm's voice on your firm's terms.

  1. 1

    Sign up your firm

    Pick a slug, set an owner password, verify your email. Under 60 seconds.

  2. 2

    Upload past work

    Drag in a zip of NDAs, MSAs, playbooks. PDF, DOCX, TXT, MD — we parse, chunk, and index everything to pgvector.

  3. 3

    Train an agent

    Click Train. A map-reduce extraction distils your firm's house style and risk rules into a single override per agent.

  4. 4

    Launch & download

    Ask the agent to review a contract or draft a clause. Get a Word .docx back, in your firm's template, with your terminology.

Built for

The workflows your team already runs

Contract review

NDA / MSA / employment / lease — flag clauses against your firm's playbook with green/amber/red classifications.

Drafting from templates

The agent fetches your golden template, fills in matter specifics, returns a tracked-change-ready DOCX.

Cross-jurisdiction triage

Auto-flag non-Indian governing law, foreign arbitration seats, indemnity caps that exceed your limits.

Compliance audit

Every inference, tool call, and HITL approval lands in an append-only log with monotonic step numbers.

For your InfoSec / procurement team

Sovereignty isn't a slide — it's in the schema.

We didn't add multi-tenancy and audit later. The platform won't boot without a tenant context. The audit log can't be skipped. The encryption can't be turned off.

Tenant-isolated by Postgres RLS

Every row of every table is filtered by tenant_id at the database. An app bug cannot leak cross-firm.

Encrypted secrets at rest

Your LLM API key is Fernet-encrypted. Decrypted only at call time; never returned by the API.

Forensic, append-only audit log

Every inference, tool call, pause, and resume gets a monotonic step number per session. Replayable end-to-end.

Indian jurisdiction defaults

Pre-tuned for INR, IST, Mumbai/Bengaluru arbitration, Indian governing law — not bolted on, baked in.

Free for design partners

Six weeks free in exchange for honest feedback.

We're onboarding our first cohort of Indian firms now. We handle the setup. You bring the corpus and tell us what we should build next.