Open Financial Agents
Reference agents, skills, and data connectors for financial-services workflows:
investment banking, equity research, private equity, and wealth management.
This repository is based on Anthropic's Claude financial-services / Claude Code
plugin templates. Most of the original agent, plugin, skill, connector, and
managed-agent cookbook files are preserved so the Claude-specific workflows
still work. This fork adds a model-neutral runtime so the same financial agent
templates can also be called through OpenAI-compatible APIs, Anthropic Messages
API, or LiteLLM. See UNIVERSAL_LLM.md.
Current delta from upstream anthropics/financial-services:
- One local commit on top of upstream:
Add universal LLM financial agents runtime.
- 21 files changed: 2,616 insertions and 37 deletions.
- Added
universal_financial_agents/, scripts/run-universal-agent.py,
scripts/free-finance-mcp.py, requirements-universal.txt, tests, and
example reports.
- The upstream Claude plugin and Managed Agent assets remain the base content.
Everything here is available two ways from one source: install it as a Claude Cowork plugin, or deploy it through the Claude Managed Agents API behind your own workflow engine. Same system prompt, same skills — you choose where it runs.
[!IMPORTANT]
Nothing in this repository constitutes investment, legal, tax, or accounting advice. These agents draft analyst work product — models, memos, research notes, reconciliations — for review by a qualified professional. They do not make investment recommendations, execute transactions, bind risk, post to a ledger, or approve onboarding; every output is staged for human sign-off. You are responsible for verifying outputs and for compliance with the laws and regulations that apply to your firm.
What's in the repo:
- Agents — named, end-to-end workflow agents (Pitch Agent, Market Researcher, GL Reconciler, …). Each ships as a Cowork plugin and as a Claude Managed Agent template you deploy via
/v1/agents.
- Vertical plugins — the underlying skills, slash commands, and data connectors, bundled by FSI vertical. Install these on their own if you just want
/comps, /dcf, /earnings and the connectors without a full agent.
- Universal LLM runtime — a Python wrapper that loads the
original child-agent templates and routes requests to OpenAI-compatible,
Anthropic, or LiteLLM providers outside Claude-specific plugin infrastructure.
Agents
Each agent is named for the workflow it runs. They're starting points: install the ones that match your work, then tune the prompts, skills, and connectors to how your firm does it.
Each agent plugin is self-contained — it bundles the skills it uses, so installing the agent is all you need.
| Function | Agent | What it does |
|---|
| Coverage & advisory | Pitch Agent | Comps, precedents, LBO → branded pitch deck, end to end |
| Meeting Prep Agent | Briefing pack before every client meeting |
| Research & modeling | Market Researcher | Sector or theme → industry overview, competitive landscape, peer comps, ideas shortlist |
| Earnings Reviewer | Earnings call + filings → model update → note draft |
| Model Builder | DCF, LBO, 3-statement, comps — live in Excel |
| Fund admin & finance ops | Valuation Reviewer | Ingests GP packages, runs valuation template, stages LP reporting |
| GL Reconciler | Finds breaks, traces root cause, routes for sign-off |
| Month-End Closer | Accruals, roll-forwards, variance commentary |
| Statement Auditor | Audits LP statements before distribution |
| Operations & onboarding | KYC Screener | Parses onboarding docs, runs the rules engine, flags gaps |
For Managed Agent deployment — agent.yaml, leaf-worker subagents, steering-event examples, and per-agent security notes — see managed-agent-cookbooks/.
Repository Layout
