Metadata-Version: 2.4
Name: agentguard47
Version: 1.3.1
Summary: Zero-dependency runtime control for production Python agents - stop loops, retry storms, and budget burn
Author-email: BMD PAT LLC <pat@bmdpat.com>
License-Expression: MIT
Project-URL: Homepage, https://agentguard47.com
Project-URL: Documentation, https://github.com/bmdhodl/agent47#readme
Project-URL: Repository, https://github.com/bmdhodl/agent47
Project-URL: Issues, https://github.com/bmdhodl/agent47/issues
Project-URL: Changelog, https://github.com/bmdhodl/agent47/releases
Keywords: agents,coding-agents,ai-agents,multi-agent,llm,guardrails,runtime-guardrails,loop-detection,budget-guard,retry-guard,runtime-enforcement,runtime-control,production-agents,coding-agent-safety,local-first,retry-storms,budget-control,langchain,openai,anthropic
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Software Development :: Testing
Classifier: Topic :: System :: Monitoring
Classifier: Typing :: Typed
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: langchain
Requires-Dist: langchain-core>=1.6.3; extra == "langchain"
Provides-Extra: langgraph
Requires-Dist: langgraph>=1.2.11; extra == "langgraph"
Requires-Dist: langgraph-checkpoint>=4.2.0; extra == "langgraph"
Requires-Dist: langgraph-sdk>=0.4.4; extra == "langgraph"
Provides-Extra: crewai
Requires-Dist: crewai>=1.15.21; extra == "crewai"
Provides-Extra: otel
Requires-Dist: opentelemetry-api>=1.44.0; extra == "otel"
Requires-Dist: opentelemetry-sdk>=1.44.0; extra == "otel"
Dynamic: license-file

<!-- Generated by scripts/generate_pypi_readme.py. Edit README.md and CHANGELOG.md instead. -->

# AgentGuard

**Stop runaway agents before they burn money.**

Zero-dependency Python kill switch for AI agents. Hard budget caps. Loop detection. Local traces. MIT.

[![PyPI](https://img.shields.io/pypi/v/agentguard47)](https://pypi.org/project/agentguard47/)
[![Downloads](https://img.shields.io/pypi/dm/agentguard47)](https://pypi.org/project/agentguard47/)
[![Python](https://img.shields.io/pypi/pyversions/agentguard47)](https://pypi.org/project/agentguard47/)
[![CI](https://github.com/bmdhodl/agent47/actions/workflows/ci.yml/badge.svg)](https://github.com/bmdhodl/agent47/actions/workflows/ci.yml)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/bmdhodl/agent47/blob/v1.3.1/LICENSE)

```bash
pip install agentguard47
```

## Getting started

### 1. Install and verify

```bash
pip install agentguard47
agentguard doctor   # package ok?
agentguard demo     # offline proof (no API keys)
```

### 2. Guard an OpenAI client

```python
from agentguard import BudgetGuard, LoopGuard, Tracer, patch_openai

budget = BudgetGuard(max_cost_usd=5.00, warn_at_pct=0.8)
loop = LoopGuard(max_repeats=3)
tracer = Tracer(service="my-agent", guards=[loop])

patch_openai(tracer, budget_guard=budget)
# every OpenAI call is now traced + budget-enforced
```

When spend crosses the hard limit, `BudgetExceeded` is raised and the run stops.

### 3. Cap a single task

Session budget can still have headroom. One goal can still be killed:

```python
with budget.goal("refund", max_cost_usd=0.50, warn_at_pct=0.8) as g:
    g.attempt()
    budget.consume(cost_usd=0.12)
    # BudgetExceeded names the goal when it crosses
```

### 4. Read the local proof

```bash
agentguard report .agentguard/traces.jsonl
agentguard incident .agentguard/traces.jsonl
```

Or scaffold a starter file:

```bash
agentguard quickstart --framework raw --write
python agentguard_raw_quickstart.py
```

## What it stops

| Problem | Guard | Exception |
|---------|-------|-----------|
| Spend blowup | `BudgetGuard` | `BudgetExceeded` |
| Same tool forever | `LoopGuard` | `LoopDetected` |
| Fuzzy / A-B-A-B loops | `FuzzyLoopGuard` | `LoopDetected` |
| Retry storms | `RetryGuard` | `RetryLimitExceeded` |
| Hung runs | `TimeoutGuard` | `TimeoutExceeded` |
| Spam calls | `RateLimitGuard` | — |
| Wallet drain (x402/USDC) | `X402SpendGuard` | `BudgetExceeded` |

Not a dashboard. Not a model router. An **in-process exception** that kills the bad run mid-flight.

### Cap your agent's x402 wallet spend

Agents that pay per-call via x402 (USDC micropayments) can drain a wallet in a
silent loop. `X402SpendGuard` wraps the payment step and refuses before paying:

```python
from agentguard import X402SpendGuard

guard = X402SpendGuard(
    max_total_usd=5.00,        # wallet cap, add period="day" for a daily reset
    max_per_endpoint_usd=1.00, # cap per resource URL
    max_per_call_usd=0.10,     # refuse any single payment above this
)
guard.charge(0.001, "https://api.example.com/search", my_x402_pay_step)
```

AgentGuard meters and refuses; it never signs or settles. Amounts come from
your x402 client. No crypto dependencies.

## Features

- **Hard stops** — exceptions inside your process, not after-the-fact alerts
- **Task-level budgets** — `BudgetGuard.goal(...)` for sub-task caps + warn hooks
- **Local traces** — JSONL by default; no network unless you opt in
- **Zero deps** — stdlib only; Python 3.9+
- **Provider patches** — `patch_openai` / `patch_anthropic`
- **Budget preflight** — provider patches refuse new requests once recorded
  usage reaches a configured cap, including sync and async clients. Use
  `budget.check()` before your own provider call and `budget.consume(...)`
  after its response. The check does not charge usage or reserve concurrent
  capacity. A response can exceed the remaining token/cost allowance; streaming
  totals are not yet tracked by the patches.
- **Framework hooks** — LangChain, LangGraph, CrewAI (optional extras)

## Local by default

- No API key required for local proof
- No network unless you configure `HttpSink`
- MIT licensed

The SDK is the free local proof path. Start local. Add hosted ingest later only if you want retained history, alerts, team visibility, spend trends, hosted decision history, or dashboard-managed remote kill signals. Local guards remain authoritative. `HttpSink` mirrors trace and decision events; it does not execute remote kill signals by itself.

## Integrations

OpenAI · Anthropic · LangChain · LangGraph · CrewAI · raw agent loops

```bash
pip install "agentguard47[langchain]"   # optional extras as needed
```

## Security

The base install declares zero runtime dependencies. `pip install agentguard47` pulls nothing, so a default install adds no third-party exposure.

Extras install third-party packages and need a separate audit. The LangChain and LangGraph extras now require Python 3.10+ and raise their minimum versions to the tested September 2026 releases. OpenTelemetry requires 1.44.0 or newer. The base SDK remains compatible with Python 3.9+.

The optional `[crewai]` extra requires CrewAI 1.15.21 or newer. Its current dependency tree still installs ChromaDB 1.1.1, with four distinct unresolved advisories: CVE-2026-45829, CVE-2026-45830, CVE-2026-45831, and CVE-2026-45833. The audit database provides no fixed version. Avoid this extra unless you have reviewed that upstream exposure. Installing AgentGuard alone does not install ChromaDB or start a server. See [the upstream advisory](https://osv.dev/vulnerability/PYSEC-2026-311) and [the release audit](https://github.com/bmdhodl/agent47/blob/v1.3.1/proof/audit-20260912/README.md).

`HttpSink` validates the address it actually connects to, retains TLS hostname verification, and refuses cross-origin redirects. It connects directly and does not use environment proxy settings. A local guard stops instrumented work in your Python process; it does not cancel an agent loop running on a provider's server. Cost estimates are not invoices; supply provider-reported cost or use strict cost resolution when an estimate is insufficient.

## Docs

- [Getting started guide](https://github.com/bmdhodl/agent47/blob/v1.3.1/docs/guides/getting-started.md)
- [Examples](https://github.com/bmdhodl/agent47/tree/v1.3.1/examples)
- [MCP server](https://github.com/bmdhodl/agent47/tree/v1.3.1/mcp-server) — `npx -y @agentguard47/mcp-server`

## Links

- PyPI: https://pypi.org/project/agentguard47/
- Issues: https://github.com/bmdhodl/agent47/issues
- AgentGuard on the web (hosted history, alerts, and MCP visibility for Claude Code, Cursor, and Codex): https://bmdpat.com/tools/agentguard?utm_source=agentguard47&utm_medium=readme&utm_campaign=touchpoints

The hosted page is an optional next step, not a requirement. The SDK stays free, local, and MIT, and the local guards stay authoritative. Nothing in this package phones home. The only network egress is a sink or exporter you configure yourself, such as `HttpSink` or an OpenTelemetry exporter.

---

MIT · Built for people who ship agents and hate surprise bills.

## Latest Release Notes (1.3.1)

(2026-09-14)

### Stop exhausted-budget retries before provider dispatch
- OpenAI and Anthropic patches now check their supplied budget before calling
  the provider, for both sync and async clients. Catching `BudgetExceeded`
  cannot send another request after the recorded budget reaches its cap.
- Added `BudgetGuard.check()`: a non-consuming check of call, token, and cost
  limits, including zero caps and the current persisted daily budget.
- Successful responses are still charged once. Reset and daily rollover allow
  new calls. Corrupt persisted counters fail closed.
- This is a preflight check, not a concurrent reservation or an estimate of
  the next response. In-flight calls can exceed token/cost caps. Streaming
  usage accounting remains outside this release.
- Reproduce the before/after behavior without network calls with
  `examples/budget_preflight_demo.py`. The provider is mocked; the installed
  AgentGuard patch, guard, and retry loop are real.

Full changelog: [CHANGELOG.md](https://github.com/bmdhodl/agent47/blob/v1.3.1/CHANGELOG.md)
