AgensGraph AI
Integrations, tools and starter material for building AI applications on
AgensGraph, the PostgreSQL-based graph
database. Every integration here runs on the
agensgraph-python driver: LangChain on 2.1,
the others on 2.0 or later.
| Integration | Package | What it gives you |
|---|---|---|
| LangChain | langchain-agensgraph |
a graph store and a vector store, three retrievers, a text2cypher chain, a LangGraph checkpointer and long-term memory store, chat message history |
| LlamaIndex | llama-index-agensgraph |
a property graph store for PropertyGraphIndex and a vector store for VectorStoreIndex |
| LightRAG | lightrag-agensgraph |
all four LightRAG storages — graph, vectors, key-value, document status — in one database |
| cognee | cognee-agensgraph |
cognee's graph store and vector store in one database |
| MCP | mcp-agensgraph-cypher, mcp-agensgraph-memory, mcp-agensgraph-data-modeling |
three Model Context Protocol servers: Cypher over a graph, a knowledge-graph memory, and graph data modeling |
Each directory has a README of its own with setup and usage, and an examples/demos/ suite
that runs on real datasets.
Installation
The agensgraph-ai package installs any combination of the integrations under one name.
Pick the ones you need:
pip install "agensgraph-ai[langchain]"
pip install "agensgraph-ai[langchain,lightrag]"
pip install "agensgraph-ai[all]"
| Extra | Installs | Import |
|---|---|---|
langchain |
langchain-agensgraph |
langchain_agensgraph |
llama-index |
llama-index-agensgraph |
llama_index_agensgraph |
lightrag |
lightrag-agensgraph |
lightrag_agensgraph |
cognee |
cognee-agensgraph |
cognee_agensgraph |
mcp |
the three mcp-agensgraph-* servers |
run as commands |
all |
all of the above |
Name at least one extra. pip install agensgraph-ai on its own installs no integrations,
and an extra that is misspelled installs none either — pip warns about that, uv does
not.
Each integration is also released on its own, so it can be installed by name instead. The
two forms produce the same environment — agensgraph-ai ships no code, and is a
convenience rather than a layer:
pip install langchain-agensgraph
pip install llama-index-agensgraph
pip install lightrag-agensgraph
pip install cognee-agensgraph
The MCP servers are commands rather than libraries, and an MCP client normally launches
them itself with uvx, which needs no install at all:
"mcpServers": {
"agensgraph-cypher": {
"command": "uvx",
"args": ["mcp-agensgraph-cypher", "--transport", "stdio"]
}
}
The mcp extra is for the other case: hosting a server yourself over HTTP or SSE.
Requirements
- Python 3.11 or later.
- A running AgensGraph: 2.14.1 or later for LangChain, 2.17 or later for the others.
SHOW agversiontells you which you have. From 2.18 a release reports four numbers, such as2.18.4.0, with-rc1on a release candidate; the first two are the line, so2.18.6.0-rc1is a 2.18 server. - The vector-backed features need the
pgvectorextension. AgensGraph does not bundle it; see how to build it.
License
Apache License 2.0 — see LICENSE.
Contact
Open an issue or a pull request.
Metadata
Release files for agensgraph-ai 0.4.0
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 | Actions |
|---|---|---|---|---|
| agensgraph_ai-0.4.0.tar.gz | 7.0 kB | Without provenance | Details for agensgraph_ai-0.4.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agensgraph_ai-0.4.0-py3-none-any.whl | Python 3 | none | any | Details for agensgraph_ai-0.4.0-py3-none-any.whl |
Total release size: 14.0 kB
Release files / agensgraph_ai-0.4.0.tar.gz
| Download URL | agensgraph_ai-0.4.0.tar.gz |
|---|---|
| Size | 7.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
144c3f964c5858321d0b0533af02ede01699f073ae469e8acdf505787d18bfbc
|
|
BLAKE2b-256 checksum How to use checksums |
896583d71c4b04a58de68e146179ee6a10b4cd3fe6a0093f5c452a4cdc7e324f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.9
|
Release files / agensgraph_ai-0.4.0-py3-none-any.whl
| Download URL | agensgraph_ai-0.4.0-py3-none-any.whl |
|---|---|
| Size | 7.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
22f68c7e75f29203901e13ef75ed07ca6fa4d882716bed074a2bbf5eb65521ac
|
|
BLAKE2b-256 checksum How to use checksums |
b21af41c345c8c2749b47a7d992a584049214e8559efdf513624992e181b994a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.9
|
Security for agensgraph-ai 0.4.0
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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.