# finledgerpoli

> AI code review for financial software that keeps your code local and backs every finding with evidence. Works with OpenAI, Anthropic, Gemini or Ollama.

## Start here

- [Quick start](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/README.md): Installation and the offline one-minute workflow.
- [AI coding agents](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/agents.md): Command selection, human approvals and host recipes; `finassist guide agents` prints the bundled guide offline.
- [CLI contracts](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/cli-contracts.md): JSON fields, output streams and exit codes; `finassist guide` lists bundled topics as JSON.

## Configure and review

- [Configuration](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/configuration.md): Path policy, profiles, providers, budgets and readiness settings.
- [JSON Schema](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/schemas/finassist.schema.json): Editor autocomplete; runtime checks remain authoritative.
- [Providers](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/providers.md): Explicit model, endpoint, disclosure and spend controls.
- [Workflows](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/workflows.md): Source review, isolated checks and approved patches.
- [Evidence-review skill](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/skills/evidence-review/SKILL.md): Portable instructions exported by `finassist export-kit`.

## Safety and evidence

- [Threat model](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/threat-model.md): Protections, trust boundaries and limits.
- [Auditing and readiness](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/readiness-and-auditing.md): Verified records, unknown outcomes and prerequisites for human review.
- [Security design](https://github.com/EleutheroiEdge/finance-dev-assistant/blob/main/docs/security-design.md): Controls for source, execution, audit and release boundaries.
