agentguard-runtime
Runtime security firewall for LangChain agents. Intercepts every tool call, checks it against a YAML policy, blocks disallowed calls, and logs everything to SQLite.
Install
pip install agentguard-runtime
Quick start
1. Write a policy file (policy.yml):
agent: pr-summarizer
rules:
- tool: GitHubTool
allow: [read]
block: [admin, write]
- tool: SlackTool
allow: [write]
- tool: "*"
block: [exec, delete]
2. Add one line to your agent:
from agentguard_runtime import AgentFirewall
agent = initialize_agent(
tools=[GitHubTool, SlackTool, ShellTool()],
llm=llm,
callbacks=[AgentFirewall(policy="policy.yml")]
)
If ShellTool tries to call exec, the agent gets a PolicyViolation and the event is logged.
CLI
# Show last 20 audit events
agentguard-runtime logs
# Start dashboard API on port 7070
agentguard-runtime dashboard
Dashboard endpoints
| Endpoint | Description |
|---|---|
GET /events |
Recent audit events (filterable by ?decision=block&agent=x) |
GET /summary |
Allowed vs blocked counts per tool today |
Policy rules
allowlist: only these actions are permitted on this toolblocklist: these actions are always rejected"*"tool: catch-all wildcard for unmatched tools- Default: if no rule matches, the call is blocked
Audit log
Events are stored at ~/.agentguard/audit.db (SQLite).
id | timestamp | agent | tool | action | input_preview | decision | reason
Dev setup
git clone <repo>
cd agentguard2
pip install -e ".[dev]"
pytest
License
MIT
Metadata
Release files for agentguard-runtime 0.1.0
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 |
|---|---|---|---|---|
| agentguard_runtime-0.1.0.tar.gz | 7.9 kB | Without provenance | Details for agentguard_runtime-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentguard_runtime-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for agentguard_runtime-0.1.0-py3-none-any.whl |
Total release size: 15.8 kB
Release files / agentguard_runtime-0.1.0.tar.gz
| Download URL | agentguard_runtime-0.1.0.tar.gz |
|---|---|
| Size | 7.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6e82a149767a570c6d91ecd5c8618ee20a59d0d9a8c4c25c21b902e9e269edde
|
|
BLAKE2b-256 checksum How to use checksums |
bf6d82662db658abe53fa57ab49a4aeaed3d9671cd609697eec791220faab5dc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.5
|
Release files / agentguard_runtime-0.1.0-py3-none-any.whl
| Download URL | agentguard_runtime-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2973e57475c5ffcda91ae794f00a72955c1148e9ed980d9259941c5aa73ff8ab
|
|
BLAKE2b-256 checksum How to use checksums |
ce8a3e8521f6c4ed7a52db683d2467d8c4dea07771019a0f127d96184717d776
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.5
|
Security for agentguard-runtime 0.1.0
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.