feat: Add OSS Lead Intelligence agent

[Samir-atra]

Description

This PR adds the Open-Source lead Intelligence Agent that transforms GitHub repository interest signals into qualified CRM contacts with enrichment data and team notifications.

The agent includes:

• 5 nodes with event_loop execution
• Multi-tool CRM integration (GitHub + Apollo + HubSpot + Slack)
• Human-in-the-loop lead review
• Configurable ICP scoring
• Conditional routing based on lead scores

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)

Related Issues

Resolves #4301

Changes Made

• Created examples/templates/oss_lead_intelligence/ directory with full agent implementation

• Added config.py with RuntimeConfig and AgentMetadata

• Added nodes/__init__.py with 5 node definitions:

  • config_intake_node: Collects user configuration (client_facing)
  • github_scan_node: Scans GitHub repositories for stargazers
  • enrich_and_score_node: Enriches profiles with Apollo and scores leads
  • review_leads_node: Presents leads for human review (client_facing)
  • crm_sync_and_notify_node: Syncs to HubSpot CRM and notifies via Slack

• Added agent.py with goal, edges, and OSSLeadIntelligenceAgent class

• Added __init__.py with all required exports

• Added __main__.py for CLI entry point

• Added mcp_servers.json for tool configuration

• Added tests/conftest.py with pytest fixtures and validation tests

• Added tests/__init__.py for test package initialization

• Added tests/test_agent.py with comprehensive agent tests

Testing

Tests run to verify the implementation:

• Unit tests pass (cd core && pytest tests/)

• Agent validation passes (graph structure, node IDs, edges)

• Goal criteria weights sum to 1.0

• All required exports present in __init__.py

• Lint passes (ruff check .)

• Manual testing performed (agent runs successfully with test configuration)

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-under areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my feature works
• New and existing unit tests pass locally with my changes

Usage

To run the agent:

cd core && uv run python -m oss_lead_intelligence run

Or use the Hive CLI:

hive run oss_lead_intelligence

Required Credentials

The agent requires the following credentials to be configured:

• GITHUB_TOKEN - GitHub Personal Access Token
• APOLLO_API_KEY - Apollo.io API key (for enrichment)
• HUBSPOT_ACCESS_TOKEN - HubSpot Private App token (for CRM sync)
• SLACK_BOT_TOKEN - Slack Bot Token (for notifications,

[github-actions]

PR Requirements Warning

This PR does not meet the contribution requirements.
If the issue is not fixed within ~24 hours, it may be automatically closed.

PR Author: @Samir-atra
Found issues: #4301 (assignees: none)
Problem: The PR author must be assigned to the linked issue.

To fix:

1. Assign yourself (@Samir-atra) to one of the linked issues
2. Re-open this PR

Exception: To bypass this requirement, you can:

• Add the micro-fix label or include micro-fix in your PR title for trivial fixes
• Add the documentation label or include doc/docs in your PR title for documentation changes

Micro-fix requirements (must meet ALL):

Qualifies	Disqualifies
< 20 lines changed	Any functional bug fix
Typos & Documentation & Linting	Refactoring for "clean code"
No logic/API/DB changes	New features (even tiny ones)

Why is this required? See #472 for details.