What is ISONGraph?
ISONGraph is an open-source AI knowledge-graph format for LLMs that serializes property graphs into a compact, tabular representation so retrieved subgraphs fit in a model's context window without wasting tokens on syntax. It targets developers building GraphRAG and agentic AI pipelines, where a graph is normally dumped as JSON or RDF and much of the prompt is consumed by brackets, quotes, and repeated keys. Benchmarked against 9 other formats, ISONGraph reports roughly 70% token savings (about 68.6% fewer tokens), 92% data-traversal accuracy, and 80% multi-hop reasoning accuracy versus 40-70% for alternative serializations, with 90% knowledge-graph QA accuracy. Beyond the format, the library provides an in-memory property-graph store with node and edge CRUD, O(1) lookups, multi-hop traversal, shortest-path search, schema validation, and an SQL-like ISONQL query language, plus optional embedding-based semantic search. It is MIT licensed and ships across Python, JavaScript/TypeScript, Rust, Go, C++, and C#, so the same format can be produced and consumed on either side of a service boundary. The Python package installs with pip install ison-graph and requires no external graph database. For teams whose GraphRAG cost and accuracy hinge on how a knowledge graph is written into the prompt, ISONGraph swaps the serialization layer rather than the retriever or the model.
What is ISONGraph used for?
Best for developers building GraphRAG or agentic AI pipelines who want to cut the tokens spent serializing a knowledge graph into LLM prompts while preserving traversal and multi-hop reasoning accuracy.
How much does ISONGraph cost?
Pros and cons
Pros
- Reports ~70% token savings (about 68.6% fewer tokens) versus verbose graph formats, benchmarked against 9 alternatives
- Strong reasoning benchmarks: 92% traversal accuracy and 80% multi-hop accuracy vs 40-70% for other serializations
- MIT licensed and multi-language (Python, JS/TS, Rust, Go, C++, C#), so producer and consumer can share one format
- In-memory property-graph store with CRUD, multi-hop traversal, shortest-path search, schema validation, and an SQL-like ISONQL query language
- No external graph database required; installs via pip install ison-graph
Cons
- New and niche format; smaller ecosystem, tooling, and community than JSON or RDF
- Requires integration work to change your GraphRAG serialization layer and adopt ISONQL
- Benchmark figures are self-reported by the maker rather than independently verified
- As a bespoke format it is less human-readable and less universally supported than standard JSON
Questions about ISONGraph
What is ISONGraph?
ISONGraph is an open-source, MIT-licensed property-graph format and in-memory graph library designed for LLM comprehension. It represents knowledge graphs in a compact tabular form so GraphRAG and agentic AI pipelines spend fewer tokens serializing graph data into prompts.
How much can ISONGraph reduce token usage?
The maker reports roughly 70% token savings (about 68.6% fewer tokens) compared with verbose graph formats, benchmarked against 9 other formats. The goal is to fit more retrieved graph data in a model's context window.
Does using ISONGraph affect reasoning accuracy?
According to the maker's benchmarks, ISONGraph reaches 92% data-traversal accuracy, 90% knowledge-graph QA accuracy, and 80% multi-hop reasoning accuracy, versus 40-70% multi-hop accuracy for alternative serializations. These figures are self-reported.
Which languages and query features does ISONGraph support?
ISONGraph ships in Python, JavaScript/TypeScript, Rust, Go, C++, and C#. It provides node and edge CRUD, O(1) lookups, multi-hop traversal, shortest-path search, schema validation, and an SQL-like ISONQL query language, with optional embedding-based semantic search. The Python package installs with pip install ison-graph.
Is ISONGraph free to use?
Yes. ISONGraph is free and open source under the MIT license, with no external graph database required.
Reviews
Sign in to rate and review ISONGraph.
Sign in to reviewNo reviews yet. Be the first to review ISONGraph!