# plurai-ai/intellagent

A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions

Repository: https://github.com/plurai-ai/intellagent
Canonical: https://ross.abutalabs.com/products/intellagent
Homepage: https://intellagent-doc.plurai.ai/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, evaluation, llmops, simulator, synthetic-data
Last push: 2026-07-14T06:23:01+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 8, longevity 48
- inputs: {"age_days": 674, "days_push": 50, "days_rel": 588, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1257, forks 154 (observed 2026-08-28T04:04:09.352773+00:00)

## What it is
IntellAgent is a Python framework for diagnosing and optimizing conversational LLM agents through simulated, realistic synthetic user interactions. It decomposes agent policies into a policy graph, generates edge-case scenarios, simulates user-agent conversations, and critiques performance to surface failure points.

## Use cases
- stress-test my chatbot agent with simulated users
- find edge cases where my LLM agent fails
- evaluate conversational agent performance before deployment
- generate synthetic user interactions for agent testing
- compare agent behavior across experiments
- diagnose policy violations in my chatbot

## When to choose
- you are deploying a conversational agent and need to uncover failure points before release
- you want automated, large-scale scenario generation and simulation instead of manual testing
- you need actionable feedback on which agent policies fail in realistic conversations

## When to avoid
- you need unit testing of non-agent code
- you want a hosted monitoring/observability platform rather than a simulation framework
- your system is not a conversational LLM agent

## Facets
- artifact type: framework
- maturity: active
- function: testing, agent-framework, machine-learning, benchmarking, data-generation
- domain: large-language-models, testing, developer-tools
- platform: python, cli
- tags: llmops, agent-evaluation, synthetic-data, conversation-simulation, chatbot-testing, ai-agents

## Member repositories
- plurai-ai/intellagent (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.352773+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:07:12.440726+00:00, confidence not recorded.
  - readme: https://github.com/plurai-ai/intellagent (fetched 2026-08-28T04:04:09.352773+00:00, sha bf0f914f9a80)
  - homepage: https://intellagent-doc.plurai.ai/ (fetched 2026-08-29T12:17:43.034366+00:00, sha 28b776ffc569)
  - site_page: https://intellagent-doc.plurai.ai/quick_start/installation (fetched 2026-08-29T12:17:43.043198+00:00, sha 4a8cf91f11f7)
- Data as of 2026-08-30T08:39:29.467469+00:00.