Legalise — DevOps skill for Claude Code
Open-source governance infrastructure for AI-assisted legal work.
How to install Legalise
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open b1rdmania/legalise and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Legalise does
Open-source governance infrastructure for AI-assisted legal work.
Alternatives in DevOps
- Claudable — Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code, Codex, Gemini CL 4k ★
- Open Agent Email — Open-source email infrastructure for AI agents: secure inboxes, REST and MCP APIs, SMTP, human approval workfl 2.1k ★
- Cccc — Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your p 1.1k ★
README
Legalise
⚠️ **Evaluation release — a reference implementation, not production software. Not for live client matters.** See [`docs/LIMITATIONS.md`](./docs/LIMITATIONS.md) for what is and isn't ready.
Open-source governance infrastructure for AI-assisted legal work. Legalise is a self-hosted workspace and reference implementation: matter policy gates model and skill calls, AI output remains a draft until named human sign-off, and actions and refusals enter a database-enforced hash chain. Exports carry the record and an offline verifier.
How it works
The loop is **draft, cite, sign-off, audit**. AI prepares an output inside a matter and cites the documents used. A named person reviews it and records a decision. The decision pins the reviewed output by hash.
flowchart LR
A[Documents
in the matter] --> B[AI drafts
+ cites sources]
B --> C[Named person
reviews]
C --> D[Sign-off
pins output by hash]
A -.-> R[(Append-only
hash-chained record)]
B -.-> R
C -.-> R
D -.-> R
Matter actions handled by Legalise write to an append-only, hash-chained audit log. The log is tamper-evident, not tamper-proof. See [`docs/TRUST.md`](./docs/TRUST.md) for the claim boundary and open gaps.
Every exported matter pack includes `audit_chain.json` and a standalone, standard-library verifier. A recipient needs only Python 3—no Legalise install, network, or database:
unzip matter-export.zip -d matter-export
cd matter-export
python3 verify_chain.py
The verifier exits non-zero if an entry was edited, removed, or reordered. Its [source](./backend/app/core/export_chain_verifier.py) and [export round-trip tests](./backend/tests/test_export_audit_chain.py) are in the repository.
What's in the repo
A self-hosted workspace for exercising the governance layer end to end:
- Documents: upload, extraction, version history, disclosure flags, and owner-scoped original-file access.
- **Chat and sk
Related Skills
AI Contributing
Open-source multi-agent governance for running multiple AI coding agents in parallel on one GitHub repo: issue
Spain AI Kit
MCP servers connecting AI applications to Spanish government open data and legal infrastructure
Platform
Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops
Blave Agent
Quant infrastructure for AI agents — a free, open-source macOS workspace where your Claude Code or Codex turns
Majiayu000
Personal GitHub profile showcasing coding-agent infrastructure, Rust systems, and open-source developer tools.
AstraBox
Open-source, self-hosted alternative to Claude Managed Agents: run Claude Code, Codex, Hermes, DeepSeek Harnes
Related Agents
License Compliance Guardian
License compliance scanning, legal risk assessment, and open source governance.
OSS
Open-source maintainer of redbar — repository governance, not the prose (that's the scribe's job). Invoke for
Audit Legal
Use this agent to conduct a legal and compliance audit (Head of Legal perspective): missing legal documents, p