How free and open tools like Hermes Agent, Google Antigravity and OpenCode can automate real legal and office tasks — working across WhatsApp, Telegram and email, around the clock — and why a new kind of “quant lawyer” matters.
A chatbot replies. An agent takes a goal, makes a plan, uses tools (search the web, read your files, send a message, run code), checks its work, and reports back — and it can keep doing this on a schedule or when something happens.
All of these are free or open-source. You “bring your own” AI model — even a private one running on your own computer.
An always-on assistant that lives on your chat apps and runs scheduled jobs. Learns by writing its own “skills.”
Open-source (MIT)Runs locallyBest for: 24/7 monitoring, reminders, WhatsApp/Telegram/email helpers.
An “agent workbench” that builds and tests things for you across an editor, terminal and browser — and shows its work.
Free previewCloudBest for: building small tools/apps, multi-step projects with proof.
A terminal assistant that can read a folder of files and do the task — and can run fully offline for privacy.
Open-source (MIT)Runs locallyBest for: document/data jobs, private/confidential work.
Friendly open helpers: Cline (in your editor), Aider (saves every change to git), Goose (reusable recipes).
Open-sourceLocal-friendlyBest for: repeatable team workflows you can share.
The “brains” (models) the agents above can use. Some, like Claude, ship ready-made legal “Skills.”
Free + paid tiersCloudBest for: the reasoning engine inside your agent.
Open “plug-ins”: Skills teach an agent a procedure; MCP connects it to your tools & data. Both open standards.
Open standardsBest for: owning your know-how instead of renting an app.
Why open tools? You keep control of your data, you're not locked into one vendor, and your team builds real skill. The honest trade-off: more setup and upkeep than a paid app. (More in Safety and Numbers.)
Hermes is one agent with one memory that you can talk to on Telegram, WhatsApp, email and more. It runs in the background all day, does jobs on a schedule, and gets better by writing its own reusable skills.
One agent · one memory · 20+ channels CONFIRMED
⏰ Always-on & scheduled. Install it once as a background service; tell it jobs in plain English. CONFIRMED
🧠 It writes its own skills. After you walk it through a task, it saves a reusable “skill” file and improves it over time — so next time it just does it. CONFIRMED (this is Hermes' real stand-out feature)
🔒 Private by default. Runs on your machine and can use a local model, so sensitive text need not leave the building. REPORTED
Every automation below is the same shape. Learn it once.
“What's my case status?” on WhatsApp.
Every day at 9am, build a briefing.
A new filing lands in the inbox.
Click any card to open the step-by-step flow. Each shows the trigger, what the agent does, the tools/channels, and who checks the result.
Setting: Adalat AI's WhatsApp helpline (launched 2026, built on Claude).
Sub-tasks automated: language detection · case lookup · plain-language summary of the latest order · English→regional-language translation · follow-up Q&A · hearing-date alerts.
Tool / channel: agent on WhatsApp · public court data | Who checks: official court record is the source of truth.
Setting: the e-Courts “Email My Case Status” + Supreme Court / Kerala HC WhatsApp alerts — the classic monitor-and-notify flow. With Hermes you can build your own.
Sub-tasks automated: polling for updates · detecting new orders/defects/listings · summarising · routing the alert to the right person.
Tool / channel: Hermes cron + email/WhatsApp | Who checks: clerk reads the summary before acting.
Sub-tasks: text extraction · key-term spotting · risk flags · each point linked to a page.
Tool: NotebookLM, or OpenCode/Goose + a PDF tool (private, local).
Sub-tasks: field definition · per-document extraction · citation linking · reusable saved agent for the next deal.
Tool: Cline/Goose + filesystem & PDF via MCP — runs over a local folder.
Output: a chronology, a timeline, and an issue map — exportable to Word/PDF.
Why it's safe: answers come only from approved sources, and legal-aid staff review chats to patch gaps.
Sub-tasks: summarise · categorise · retrieve the right info · draft · notify. A local version uses Ollama so nothing leaves your computer.
Tool: Hermes, or an n8n template + Ollama + Telegram.
Set it in one sentence: “Every morning at 8, summarise overnight email and send me the top 5 things to do, on Telegram.”
Great for: compliance teams and registries tracking UGC/DU/government circulars.
Why it matters: a searchable, citeable “memory” of your office — built with open tools (LangChain + a local model), so confidential files stay in-house.
REAL = documented deployment/capability · TEMPLATE = published, runnable template (not a named end-user) · Hermes = native Hermes feature. Vendor time-savings are claims, not audited facts.
Filter by area. Colour shows how far it can go today: Full‑ish light check · Partial agent drafts, you finish · Human decides agent assists only.
| Category | Example sub-tasks | How far | Best-fit tool | Watch out for |
|---|---|---|---|---|
| Legal research | find authorities, synthesise, check citations | Human decides | NotebookLM / RAG | fabricated cases |
| Drafting | letters, notices, first-draft briefs | Partial | Claude / Gemini | tone, accuracy |
| Document review | contracts, NDAs, due diligence | Partial | Cline/Goose + MCP | missed clauses |
| Case monitoring | watch cause-lists, deadlines, alerts | Full‑ish | Hermes (24/7) | wrong data |
| Litigation support | chronologies, claim charts, deposition prep | Partial | RAG + agents | source fidelity |
| Court admin | cause lists, transcription, translation | Partial | Adalat-style / SUVAS | confidentiality |
| Intake & Q&A | front-desk questions, self-help | Human decides | RAG chatbot | wrong advice |
| Inbox & comms | triage, summarise, draft replies | Partial | Hermes / n8n | over-auto-reply |
| Daily briefings | scan, rank, send a digest | Full‑ish | Hermes cron | noise |
| Monitoring | regulations, websites, folders | Full‑ish | scheduled agent | stale sources |
| Knowledge base | ask across your own files (RAG) | Partial | local RAG | access control |
| Data wrangling | clean, dedupe, convert files | Full‑ish | OpenCode | silent errors |
AI saves serious time on the right tasks. But on complex work an expert already knows well, it can even slow you down — so we measure honestly and always verify.
Sources: Noy & Zhang 2023; Brynjolfsson et al.; METR 2025. Faster ≠ always — context matters.
Per-seat SaaS prices are third-party estimates; open/self-host shifts cost to people & maintenance.
of legal tasks are exposed to automation (Goldman 2023) — a ceiling, not a guarantee.
hallucination rate even in legal-grade AI research tools (Stanford) — so verify, always.
of agent projects may be cancelled by 2027 (Gartner) — skills & governance decide success.
A quant lawyer — like the “quants” who reshaped finance — is a legally trained person who can also command AI: write a Skill, connect a tool, build a private RAG, supervise the result with a lawyer's judgement. Not everyone becomes an engineer; the institution builds a spectrum of fluency.
Choose a weekly chore — say, summarising circulars — and do it once with NotebookLM or OpenCode.
Install Hermes, connect Telegram, and schedule a single daily briefing.
Use an AI to draft a routine notice — then edit, verify, and send.