Constellation
Graph-backed code intelligence for your AI assistant.
Constellation turns your codebase into a queryable knowledge graph, giving AI assistants the structural understanding they need to reason about real software — not just the plain text.
Why Constellation?
Text search tells you where a string appears, *everywhere* that string appears. Constellation tells you the exact location of the symbol in question, what it means, what calls it, and what breaks if you change it. Before your assistant edits a function, it can ask:
- Where is this defined, and where is it used across the codebase?
- What's the blast radius of this change?
- Which modules have circular dependencies or dead code?
- How does data flow through the call graph?
Answers come from a semantic graph, not a grep loop.
One Tool, Countless Capabilities
A single `code_intel` tool exposes a rich JavaScript API as a "Code Mode" tool, allowing AI agents to craft complex composite queries.
Learn more
Agno
Agno is a lightweight framework for building agents with memory, knowledge, tools, and reasoning. Developers use Agno to build reasoning agents, multimodal agents, teams of agents, and agentic workflows. Agno also provides a beautiful UI to chat with agents and tools to monitor and evaluate their performance. It is model-agnostic, providing a unified interface to over 23 model providers, with no lock-in. Agents instantiate in approximately 2μs on average (10,000x faster than LangGraph) and use about 3.75KiB memory on average (50x less than LangGraph). Agno supports reasoning as a first-class citizen, allowing agents to "think" and "analyze" using reasoning models, ReasoningTools, or a custom CoT+Tool-use approach. Agents are natively multimodal and capable of processing text, image, audio, and video inputs and outputs. The framework offers an advanced multi-agent architecture with three modes, route, collaborate, and coordinate.
Learn more
Ferret
An End-to-End MLLM that Accept Any-Form Referring and Ground Anything in Response.
Ferret Model - Hybrid Region Representation + Spatial-aware Visual Sampler enable fine-grained and open-vocabulary referring and grounding in MLLM.
GRIT Dataset (~1.1M) - A Large-scale, Hierarchical, Robust ground-and-refer instruction tuning dataset.
Ferret-Bench - A multimodal evaluation benchmark that jointly requires Referring/Grounding, Semantics, Knowledge, and Reasoning.
Learn more
Stardog
With ready access to the richest flexible semantic layer, explainable AI, and reusable data modeling, data engineers and scientists can be 95% more productive — create and expand semantic data models, understand any data interrelationship, and run federated queries to speed time to insight. Stardog offers the most advanced graph data virtualization and high-performance graph database — up to 57x better price/performance — to connect any data lakehouse, warehouse or enterprise data source without moving or copying data. Scale use cases and users at lower infrastructure cost. Stardog’s inference engine intelligently applies expert knowledge dynamically at query time to uncover hidden patterns or unexpected insights in relationships that enable better data-informed decisions and business outcomes.
Learn more
