agentfoundry 1.4.10

AgentFoundry: A modular autonomous AI agent framework

AIgent

AIgent is a modular, extensible AI framework designed to support the construction and orchestration of autonomous agents across a variety of complex tasks. The system is built in Python and leverages modern AI tooling to integrate large language models (LLMs), vector stores, rule-based decision logic, and dynamic tool discovery in secure and performance-conscious environments.

Features

• Modular agent architecture with support for specialization (e.g., memory agents, reactive agents, compliance agents)
• Cython-compiled backend for performance and IP protection
• Integration with popular frameworks such as LangChain, ChromaDB, and OpenAI
• Support for licensed or embedded deployments via license file verification or compiled-only distribution
• Configurable with runtime enforcement of execution licenses (RSA-signed, machine-bound)

Use Cases

AIgent is designed to serve as a core intelligence engine for:

• Secure enterprise AI platforms (e.g., QuantumDrive)
• Compliance monitoring and rule-based alerting systems
• Conversational interfaces with dynamic tool execution
• Embedded agents in SaaS and on-premise environments

Requirements

• Python 3.11+
• Cython
• Compatible dependencies (see requirements.txt)

Required Configuration (Fail‑Fast)

This project does not use dummy/stub fallbacks. Missing config or dependencies cause explicit errors. Configure these before running:

• VECTORSTORE.PROVIDER: Set to faiss or chroma.
• OPENAI_API_KEY: Required for components that use OpenAI embeddings (e.g., ThreadMemory; FAISS provider uses OpenAI embeddings).
• FAISS.INDEX_PATH: When VECTORSTORE.PROVIDER=faiss, must point to an existing FAISS index created by your ingestion pipeline.
• CHROMA.URL or CHROMA.HOST/CHROMA.PORT, else local CHROMADB_PERSIST_DIR is used for embedded Chroma.
• KGraph (duckdb_sqlite) requires duckdb, adbc-driver-duckdb, and adbc-driver-manager Python packages.
• Optional: SERPAPI_API_KEY for Discovery; OLLAMA.HOST/OLLAMA.MODEL for Ollama LLM; GEMINI_API_KEY (or GOOGLE_API_KEY) and GEMINI_MODEL (defaults to gemini-3-pro-preview) when using the Gemini provider.

You can set these via environment variables (e.g., VECTORSTORE_PROVIDER, OPENAI_API_KEY, CHROMA_URL) or in the TOML at ~/.config/agentfoundry/agentfoundry.toml (copied from agentfoundry/resources/default_agentfoundry.toml).

Example TOML entries:

VECTORSTORE.PROVIDER = "chroma"  # or "faiss"

# Unified persistence directory for embedded Chroma (DuckDB)
CHROMADB_PERSIST_DIR = "~/.config/agentfoundry/chromadb"

[FAISS]
INDEX_PATH = "~/.config/agentfoundry/faiss_index"

Author

Christopher Steel
AI Practice Lead, AlphaSix Corporation
Founder, Syntheticore, Inc.
Email: [e-mail]

Licensing and Legal Notice

© Syntheticore, Inc. All rights reserved.

This software is proprietary and confidential.
Any use, reproduction, modification, distribution, or commercial deployment of AIgent or any part thereof requires explicit written authorization from Syntheticore, Inc.

Unauthorized use is strictly prohibited and may result in legal action.

---

For licensing inquiries or permission to use this software, please contact:
📧 [e-mail]

Gradio Chat Interface

A simple Gradio-based chat interface for interacting with the HybridOrchestrator agent.

Prerequisites

• Ensure you have set your OpenAI API key:

export OPENAI_API_KEY=<your_api_key>

Running the App

python gradio_app.py

The interface will be available at http://localhost:7860 by default.

API Server

Genie can be accessed programmatically via a FastAPI‑based HTTP API. Two main endpoints are provided:

• POST /v1/chat: Send or continue a multi‑turn conversation with Genie. Accepts JSON payload with conversation history and returns the assistant reply and updated history.
• POST /v1/orchestrate: Discover APIs and execute a main task across all agents. Returns aggregated results.
• GET /health: Health check endpoint.

Prerequisites

• Ensure you have set your OpenAI API key:

export OPENAI_API_KEY=<your_api_key>

• Install FastAPI and Uvicorn (if not already):

pip install fastapi uvicorn[standard]

Running the API

python api_server.py
# Or with auto‑reload during development:
uvicorn api_server:app --reload --host 0.0.0.0 --port 8000

Interactive API docs will be available at http://localhost:8000/docs

• For Microsoft Graph access (entra_tool), forward the SPA's bearer token in the Authorization: Bearer <token> header; the API server injects it into the orchestrator config as entra_user_assertion for on-behalf-of token exchange.

Logging & Debugging

AgentFoundry automatically logs events to a file and rotates it on each startup.

By default, logs are written to agentfoundry.log at INFO level. You can customize logging behavior via environment variables:

export AGENTFOUNDRY_LOG_FILE=agentfoundry.log
export AGENTFOUNDRY_LOG_LEVEL=DEBUG  # or INFO, WARNING, ERROR

Upon each restart of the application or API server, if agentfoundry.log already exists, it is renamed to agentfoundry.log.YYYYMMDDHHMMSS for archival, and a fresh log file is started. View live logs in agentfoundry.log and inspect past runs in the timestamped backup files.

Quick Smoke Test (Chroma, local persistence)

This verifies vector search without external APIs:

export VECTORSTORE_PROVIDER=chroma
export CHROMADB_PERSIST_DIR="$(mktemp -d)"
python - <<'PY'
from agentfoundry.vectorstores.factory import VectorStoreFactory
vs = VectorStoreFactory.get_store(org_id='smoke')
vs.add_texts(["hello world"], metadatas=[{"org_id":"smoke"}], ids=["1"])
hits = vs.similarity_search("hello", k=1, filter={"org_id":"smoke"})
print("Hits:", [h.page_content for h in hits])
PY

Expected: Hits: ['hello world'].

Notes:

• ThreadMemory requires OPENAI_API_KEY and will fail fast if not set.
• FAISS provider raises if FAISS.INDEX_PATH does not exist; initialize with your ingestion tooling.