# Quick start

```bash
pip install "inter-agent-guard[all,otel]"
python scripts/download_release_model.py   # ~164 MB INT8 ONNX from GitHub Releases
agentguard status
```

```python
from agentguard import AgentGuard, CapabilityManifest

guard = AgentGuard(
    risk_threshold=0.85,
    task_objective="Analyse Q3 competitor pricing",
    audit_log_path="./audit.jsonl",
    require_ml_model=True,  # after download_release_model.py
)
guard.register_agent(
    "research-agent",
    CapabilityManifest.from_yaml("manifests/research_agent.yaml"),
)
secured = guard.wrap(my_langgraph_graph)
```

Without the ONNX model, rule filtering, trust attestation, and capability
enforcement still run. Set `require_ml_model=True` only after the model is installed.

## Inter-agent messages (trust attestation)

Trust attestation is **on by default**. Inter-agent payloads must be signed
with a recipient-bound envelope before `inspect_message` will forward them:

```python
payload = b"Research summary ready for internal report."
text = payload.decode()
sig = guard.sign_payload("researcher", payload, recipient_id="writer")
decision = guard.inspect_message(
    "researcher",
    "writer",
    text,
    payload,
    signature=sig,
)
```

`sign_payload` requires ``recipient_id`` matching the recipient passed to
``inspect_message``. Unsigned messages are **BLOCK**ed; legacy raw 64-byte
signatures are rejected.

For unsigned boundaries (user input, framework hooks), use
``inspect_content(sender_id, recipient_id, message)`` instead — it runs the
rule filter, ML scorer, and consistency check without trust verification.

## LangChain agents

For LangChain 1.0 `create_agent`, use the official middleware integration:

```python
from langchain.agents import create_agent
from agentguard import AgentGuard
from agentguard.adapters.langchain import AgentGuardMiddleware

guard = AgentGuard(task_objective="Analyse Q3 competitor pricing")
agent = create_agent(
    model="gpt-5.5",
    tools=[...],
    middleware=[AgentGuardMiddleware(guard, agent_id="researcher")],
)
```

User input is scanned before the first model call, every tool output is
inspected for indirect injection before the model sees it, and capability
manifests registered under `agent_id` are enforced before tools execute.
Requires `pip install "inter-agent-guard[langchain]"`.

## Links

- **Docs:** https://inter-agent-guard.readthedocs.io/
- GitHub: https://github.com/nizba06/agentguard
- PyPI: https://pypi.org/project/inter-agent-guard/
- Demo: https://github.com/nizba06/inter-agent-guard-demo
- Dataset: https://huggingface.co/datasets/Nizba/agentguard-benchmark-v1