vigil-client
Python client for Vigil Cloud — cognitive infrastructure for AI agents.
Install
pip install vigil-agent-client
Quick Start
from vigil_client import Vigil
v = Vigil(api_key="vgl_...")
# Emit a signal
v.signal("deploy complete", agent="my-bot")
# Boot with compiled awareness
context = v.boot()
print(context["awareness"])
# End session with handoff
v.handoff(
agent="my-bot",
summary="Deployed auth v2",
files=["auth.py", "middleware.py"],
next_steps=["Monitor error rates", "Update docs"],
)
Environment Variables
export VIGIL_API_KEY=vgl_...
export VIGIL_API_URL=https://app.vigil-agent.com # optional, this is the default
# Reads from env automatically
v = Vigil()
API Reference
| Method | Description |
|---|---|
v.signal(content, agent, signal_type) |
Emit a signal |
v.boot() |
Boot with compiled awareness |
v.compile() |
Force awareness compilation |
v.status() |
Get current awareness |
v.signals(hours, limit, agent) |
Read recent signals |
v.handoff(agent, summary, files, decisions, next_steps) |
End session |
v.resume(agent) |
Resume from last handoff |
v.chain(limit) |
Get handoff briefing |
v.focus_add(description, priority) |
Add focus item |
v.focus_list() |
List active focus |
v.know(key, value, category) |
Store knowledge |
v.recall(query) |
Search knowledge |
v.frames() |
List frames |
v.triggers() |
List triggers |
v.usage() |
Get usage and limits |
v.agents() |
List known agents |
v.mcp_health(server) |
MCP server health stats |
v.mcp_errors(server, limit) |
Recent MCP tool errors |
v.mcp_latency(server, hours) |
Latency percentiles (p50/p95/p99) |
Zero Dependencies
Uses only Python stdlib (urllib, json). No requests, no httpx — just works.
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for vigil-agent-client 0.2.0
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 |
|---|---|---|---|---|
| vigil_agent_client-0.2.0.tar.gz | 5.1 kB | Without provenance | Details for vigil_agent_client-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vigil_agent_client-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for vigil_agent_client-0.2.0-py3-none-any.whl |
Total release size: 10.9 kB
Release files / vigil_agent_client-0.2.0.tar.gz
| Download URL | vigil_agent_client-0.2.0.tar.gz |
|---|---|
| Size | 5.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8ce6e3032060e3b48e922cb359356c1d2d29d256a5c666e271f62171af6096c8
|
|
BLAKE2b-256 checksum How to use checksums |
1111dfa8063a6898031b6bd4d8e1af4539106c122edd314540518a69e27b4ac2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / vigil_agent_client-0.2.0-py3-none-any.whl
| Download URL | vigil_agent_client-0.2.0-py3-none-any.whl |
|---|---|
| Size | 5.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
dcadc9ac59bfafcd5e03bce2a7e9c56d09260a4c5fa3146bbc023cce26419766
|
|
BLAKE2b-256 checksum How to use checksums |
2ca096fd95a441156c03f41ac37a40fbe7f968ed60bf3f3f23bcfe9a95a78cf4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for vigil-agent-client 0.2.0
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.
