Skip to main content

llamaindex-agentid

PyPI version License: MIT

AgentID identity and trust for LlamaIndex — sign every query response, discover agents by capability, verify output provenance.

pip install llamaindex-agentid

Query engine wrapper

Wrap any LlamaIndex query engine — every response is automatically signed with your agent's Ed25519 key:

import os
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llamaindex_agentid import AgentIDQueryEngine

documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)

# First run: creates a new identity. Save the DID to an env var.
engine = AgentIDQueryEngine(
    query_engine=index.as_query_engine(),
    name="research-agent",
    capabilities=["research", "summarization"],
    owner="team@company.com",
    registry_url="https://api.agentid-protocol.com",
)
print(f"DID (save this): {engine.did}")

# Subsequent runs: reload the same identity
engine = AgentIDQueryEngine(
    query_engine=index.as_query_engine(),
    did=os.environ["MY_AGENT_DID"],
    name="research-agent",
    capabilities=["research", "summarization"],
    owner="team@company.com",
    registry_url="https://api.agentid-protocol.com",
)

response = engine.query("What are the main AI safety concerns?")
print(response.response)

# Verify the response came from who it claims
assert engine.verify_response(response)  # True

# Or verify from another process using only the DID
from agentid import Agent
Agent.verify_from_did({
    "payload":   response.metadata["_agentid_payload"],
    "signature": response.metadata["_agentid_signature"],
})  # True

Agent tools

Add AgentID discovery and verification tools to any LlamaIndex ReAct agent:

from llama_index.core.agent import ReActAgent
from llama_index.llms.openai import OpenAI
from llamaindex_agentid import get_agentid_tools

tools = get_agentid_tools(registry_url="https://api.agentid-protocol.com")

agent = ReActAgent.from_tools(
    tools,
    llm=OpenAI(model="gpt-4o"),
    verbose=True,
)

# The agent can now:
# - Call agentid_find("web-search") to discover other agents
# - Call agentid_verify(signed_message) to verify messages from other agents
response = agent.chat("Find a web-search agent and tell me what it can do")

Response metadata

Every response from AgentIDQueryEngine.query() includes:

Key Description
_agentid_did Signer's DID
_agentid_signature Base64 Ed25519 signature
_agentid_payload Signed payload (pass to Agent.verify_from_did)

License

MIT

Metadata

Release files for llamaindex-agentid 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llamaindex-agentid 0.1.0
File Size Uploaded
llamaindex_agentid-0.1.0.tar.gz 6.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for llamaindex-agentid 0.1.0
File Interpreter ABI Platform
llamaindex_agentid-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 13.4 kB

Release files / llamaindex_agentid-0.1.0.tar.gz

Download URL llamaindex_agentid-0.1.0.tar.gz
Size 6.3 kB
Tags Source
SHA-256 checksum
How to use checksums
2a5b8df6324d5fe998ecff756d3aea8a2c2ab0242105f50d9837f37694170139
BLAKE2b-256 checksum
How to use checksums
27b85d89fefbfaf257c8cce0c0019a51d99e5369edb5836c340101649373e927
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Release files / llamaindex_agentid-0.1.0-py3-none-any.whl

Download URL llamaindex_agentid-0.1.0-py3-none-any.whl
Size 7.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
02d7883b5f25fd497aa73235b06d0b7b9051b103d7e220d0341f990014739176
BLAKE2b-256 checksum
How to use checksums
3c8cda6a176e97aaa99ba5ffad7f031cf033d1cbbfaeee7aa459ca7354e413be
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page