pisama 0.6.1

Multi-agent failure detection for production AI systems

Pisama

Find and fix failures in AI agent systems. No LLM calls required.

Pisama ships heuristic detectors that apply across frameworks including n8n, LangGraph, Dify and OpenClaw, with per-platform gating (for example coordination runs only on multi-agent platforms). They run locally with zero LLM cost on the heuristic tier.

Install

pip install pisama

Usage

from pisama import analyze

result = analyze("trace.json")  # also accepts dicts and JSON strings

for issue in result.issues:
    print(f"[{issue.type}] {issue.summary} (severity: {issue.severity})")
    print(f"  Fix: {issue.recommendation}")

CLI

pisama analyze trace.json          # Analyze a trace
pisama watch python my_agent.py    # Watch a live agent (pip install "pisama[auto]")
pisama replay <trace-id>           # Re-run detection on stored traces
pisama smoke-test --last 50        # Batch test recent traces
pisama detectors                   # List all core detectors
pisama mcp-server                  # Start MCP server (pip install pisama[mcp])

MCP Server

Works in Cursor, Claude Desktop, and Windsurf. No API key is needed:

{
  "mcpServers": {
    "pisama": { "command": "pisama", "args": ["mcp-server"] }
  }
}

Optional extras

The base pisama install has zero-cost heuristic detection covered. Two extras add opt-in functionality on top.

Auto-instrumentation: pisama[auto]

Zero-code tracing for LLM calls. init() patches supported clients (Anthropic, OpenAI) so every call after it emits an OTEL trace Pisama can analyze, no manual instrumentation needed.

pip install "pisama[auto]"

import pisama.auto

pisama.auto.init(api_key="ps_...")

# All subsequent LLM calls are automatically traced
import anthropic
client = anthropic.Anthropic()
response = client.messages.create(...)  # traced automatically

This used to require the standalone pisama-auto package. That package still works and stays fully supported for existing installs; pisama[auto] is the same code, folded into the base package so there is one less dependency to track. New projects should install it this way.

Agent hooks and tools: pisama[agents]

Real-time hooks, tools, and self-check utilities for agent runtimes (built for the Claude Agent SDK), wired to Pisama's detection infrastructure for in-loop failure prevention rather than after-the-fact analysis.

pip install "pisama[agents]"

from pisama.agents import pre_tool_use_hook, post_tool_use_hook

agent.hooks.pre_tool_use = pre_tool_use_hook
agent.hooks.post_tool_use = post_tool_use_hook

Active self-check is available the same way:

from pisama.agents import check

result = await check(
    output="The server is healthy based on the metrics.",
    context={"query": "Is auth-service down?", "sources": [...]},
)
if not result["passed"]:
    ...  # revise output based on result["issues"]

This used to require the standalone pisama-agent-sdk package. That package still works and stays fully supported for existing installs; pisama[agents] is the recommended path for new projects, one package instead of two.

Detectors

Core detectors, gated per platform (n8n, LangGraph, Dify, OpenClaw and others). A representative selection:

Detector	What It Catches
loop	Infinite loops, retry storms, stuck patterns
coordination	Deadlocked handoffs, message storms
hallucination	Factual errors, fabricated tool results
injection	Prompt injection, jailbreak attempts
corruption	State corruption, type drift
persona_drift	Persona drift, role confusion
derailment	Task deviation, goal drift
context	Context neglect, ignored instructions
specification	Output vs. requirement mismatch
communication	Inter-agent message breakdown
decomposition	Poor task breakdown, circular dependencies
workflow	Unreachable nodes, missing error handling
completion	Premature completion, unfinished work
withholding	Suppressed findings, hidden errors
convergence	Metric plateau, regression, thrashing
overflow	Context window exhaustion
propagation	Silent error propagation across steps
citation	Fabricated citations and source misattribution
routing	Inputs misrouted to the wrong specialist agent
mcp_protocol	MCP tool-communication failures

Links

• Documentation
• GitHub
• Platform

License

MIT

Source boundary

This repository is the public source for the MIT-licensed pisama Python package. It does not contain the Pisama Cloud backend, dashboard, calibration data, managed detection tiers, or paid automation.