Vanaras AI — Agent Framework
Vanaras is a Local First, extensible agent framework for programmatic code tasks, tool execution, and memory-backed context. It provides a minimal planner, a code executor, a memory store (FAISS), and a sandboxed tools layer that agents call to read/write files, run code, and apply patches.
📚 Documentation
Full documentation is available at vanaras.ai (or run locally with npm start in website/).
🚀 Key Features
- Local First: Designed to run with local LLMs (Ollama/Llama 3.1) by default. Privacy by design.
- Agentic Workflow: Don't just run scripts—orchestrate Planner, Developer, Critic, and Validator agents.
- Templates: 9 built-in templates for common use cases (RAG, Web Scraper, ETL, etc.).
- Memory: Built-in vector memory (FAISS) for long-term context.
- Dashboard: Real-time UI to monitor agent activities.
🛠️ Installation
pip install vanaras-agent-framework
Configure LLM (Local First)
- Install Ollama: ollama.com
- Pull Model:
ollama pull llama3.1 - Run: Vanaras connects to
localhost:11434automatically.
(Optional: Set VANARAS_LLM_URL and VANARAS_API_KEY for OpenAI)
⚡ Quick Start with CLI
The Interactive CLI is the heart of Vanaras. Just type what you want:
vanaras init my_agent
cd my_agent
vanaras run
Example Session:
🤖 Vanaras Agent Framework
💬 How can I help you today?
> Create a stock price tracker for AAPL and GOOGL. Save the report to markdown.
✨ Working on it...
[Planner] Creating plan...
[Developer] Writing code...
[Critic] Reviewing code...
✅ Done!
📖 Tutorials
We have comprehensive, fully agentic tutorials for every template:
- Financial Analyst: Build an ETL pipeline.
- Web Scraper: Track competitor prices.
- Doc Generator: Auto-generate documentation.
- RAG Agent: Chat with legal documents.
- Code Analyzer: Audit legacy code.
- Multi-Agent Crew: Orchestrate a marketing team.
- Testing Framework: Auto-generate test suites.
- API Client: Generate SDKs from OpenAPI.
- CLI App: Build custom CLI tools.
Enterprise Features 🔒
Vanaras Enterprise provides:
- Security: SSO, RBAC, Audit Logging
- Scalability: Distributed execution
- Compliance: SOC 2, GDPR
- Support: 24/7 SLA
License
Open Source: Apache 2.0 Enterprise: Proprietary
Community
Made with ❤️ by Vanaras AI
Metadata
Release files for vanaras-agent-framework 2.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| vanaras_agent_framework-2.1.0.tar.gz | 36.7 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| vanaras_agent_framework-2.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 73.4 kB
Release files / vanaras_agent_framework-2.1.0.tar.gz
| Download URL | vanaras_agent_framework-2.1.0.tar.gz |
|---|---|
| Size | 36.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
653a705f7bd6ef2785cc8a7d66ee88e176d120d6a2bd4639ed991827ddbe438c
|
|
BLAKE2b-256 checksum How to use checksums |
726f52881cb7a0922c724a548096a167500c07468e092200bfdfdacbf73afddd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Release files / vanaras_agent_framework-2.1.0-py3-none-any.whl
| Download URL | vanaras_agent_framework-2.1.0-py3-none-any.whl |
|---|---|
| Size | 36.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
099da572a16f8c6137b95ea1f3936d40e2b4f12e5cf7d935e4a77b4e691dca72
|
|
BLAKE2b-256 checksum How to use checksums |
99c91e01318b1b60a1dc0cd1df9a56e69e1e80198fc53d06284d4f3b7d34e816
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Security for vanaras-agent-framework 2.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.