AgentOps

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

AgentOps

AgentOps is a comprehensive platform designed for monitoring, debugging, and optimizing AI agents in both development and production environments. It provides advanced tools such as session replays, metrics dashboards, and custom reporting, enabling developers to track the performance, cost, and interactions of their AI agents in real-time.

Some of the out-of-the-box integrations include:

CrewAI,
Autogen,
Langchain,
Cohere,
LiteLLM,
MultiOn.

This wide compatibility ensures seamless integration with a diverse range of AI systems and development environments.

General
Author	AgentOps, Inc.
Release Date	2023
Website	https://www.agentops.ai/
Documentation	https://docs.agentops.ai/v1/introduction
Technology Type	Monitoring Tool

Key Features

LLM Cost Management: Track and manage the costs associated with large language models (LLMs).
Session Replays: Replay agent sessions to analyze interactions and identify issues.
Custom Reporting: Generate tailored reports to meet specific analytical needs.
Recursive Thought Detection: Monitor recursive thinking patterns in agents to ensure optimal performance.
Time Travel Debugging: Debug and audit agent behaviors at any point in their operational timeline.
Compliance and Security: Built-in features to ensure that agents operate within security and compliance standards.

Start Building with AgentOps

AgentOps offers developers powerful tools to enhance the monitoring and management of AI agents. With easy integration through SDKs, it provides real-time insights into the performance and behavior of agents. Developers are encouraged to explore community-built use cases and applications to unlock the full potential of AgentOps.

👉 Start building with AgentOps

👉 Examples

Edit on GitHub

AgentOps AI technology page Hackathon projects

Discover innovative solutions crafted with AgentOps AI technology page, developed by our community members during our engaging hackathons.

Routengo

The DevFleet Orchestrator Engine is a lightweight, concurrent Go agent designed to solve diverse query categories under strict token and execution constraints. It implements an intelligent multi-tiered router that classifies inputs into categories (such as math, sentiment, factual, summarization, and coding) and routes them cost-efficiently. For low-level queries like basic arithmetic, a zero-token local AST math solver evaluates equations instantly without reaching the cloud. Ambiguous sentiment queries trigger a local sentiment polarity classifier that utilizes a 1-token verification gate ("YES" or "NO") on a cheap Tier 1 model before escalating. Highly complex logical or code queries are routed dynamically to robust Tier 3 models. To prevent token waste, the engine enforces server-side max_token caps, strips reasoning tags (think blocks) and markdown fences, and runs a post-completion output auditor that cleans preambles, ensures sentence counts, normalizes lists, and grammatically formats truncated bullet points. Built on a thread-safe deduplication cache and wrapped in a scratch Docker image with root certificates, it guarantees high accuracy and zero TLS handshake overhead.

PrepAI

This project is an AI-driven interview preparation platform combining agent-based orchestration and web tooling. CrewAI agents (agent1/agent2) run task-driven workflows that use tools for curriculum access, web research, and database storage. A FastAPI backend orchestrates kickoff routes and coordinates asynchronous agent execution. LLM integration is provided via litellm/Fireworks, with provider-specific handling for request compatibility. The frontend (Vite + React) hosts session UIs and authentication, while backend utilities seed and manage the database. Tests cover curriculum, database, and web access components. The system aims to generate targeted practice sessions, quizzes, and evaluative feedback tailored to role, topic, and skill level.

Clip Insighs

Clip Insights is a Chrome extension that transforms the way you learn from videos by turning hours of footage into fast, actionable notes and insights. Instead of scrubbing through long videos to find what matters, users can take screenshots, make notes, get rapid AI-generated summaries, along with key points extracted from any video. The extension supports interactive video chat, letting viewers ask questions directly about the content and receive instant, real-time answers. Users can also capture instant screenshots at any moment in a video and take timestamped, unlimited notes right inside the extension. Everything - summaries, screenshots, and notes - can be compiled and exported into a single downloadable PDF with one click, making it easy to save, organize, and revisit learning material. Built for students, researchers, and lifelong learners, Clip Insights streamlines video-based learning into one seamless, distraction-free workflow.

Mission Control: Earthquake Response

Mission Control is a multi-agent AI disaster response coordinator built for the AMD Developer Hackathon. When an earthquake strikes, five specialized AI agents — Overwatch (Commander), Sentinel (Intelligence), Atlas (Logistics), Pulse (Medical), and Aegis (Risk) — spring into action. Each agent analyzes real-time data from USGS seismic feeds, OpenStreetMap infrastructure mapping, and OpenWeatherMap weather conditions. They debate resource allocation, hospital capacity, evacuation routes, and risk factors, then the Commander synthesizes their analyses into an evolving mission plan with actionable steps. Every agent response is validated against real data through a citation scoring system that proves the AI is actually using live information — not hallucinating. The system is built on a dual-path LLM architecture targeting AMD MI300X GPUs via ROCm — we successfully loaded Gemma 4 26B on the AMD instance using HuggingFace transformers with a custom grouped_mm compatibility patch, and we're optimizing further with Unsloth + llama.cpp for Radeon to maximize inference throughput. The production path runs on OpenRouter with the same Gemma 4 model, demonstrating the system works end-to-end today while being engineered to scale on AMD compute. The system processes 25+ events per scenario with staggered timestamps, streaming everything to a command center dashboard over WebSocket.

Multi-Agent Ethical Document Reviewer

Ethical Agents is an intelligent document review platform that automatically screens any document — policy, AI system design, research proposal, or product specification — for ethical risk before publication. The system runs five specialist AI agents in parallel, each responsible for a different risk domain: Bias, Privacy, Security, Compliance, and Transparency. Every agent evaluates the document against a curated Domain Knowledge Repository of risk fields using a four-component scoring model that measures keyword coverage, term density, and topical prominence. A governance multiplier then adjusts scores based on the document's ethical posture — rewarding explicit safeguards like human oversight and audit trails, and penalising dismissals of safety mechanisms. A parent orchestrator aggregates the five domain scores using a ceiling-pull model, ensuring a single severely problematic domain cannot be outweighed by clean ones. The final output includes a clear Publish or Do Not Publish decision, an overall risk score out of 100, per-domain breakdowns, a list of every high-risk field with the reason it was flagged, and concrete remediation steps. The system also features a self-improving learning loop: when connected to a Fireworks AI LLM, agents can identify novel risk concepts not yet in their knowledge base and permanently extend it. A calibration pipeline with automated grid search keeps scoring accuracy tuned against labelled test documents. The React frontend displays all results in real time and loads the full analysis history from the backend on startup.

AgentOS:Adversarial Multi-Agent Knowledge Platform

AgentOS is an enterprise-grade Agentic Knowledge Platform designed to transform how organizations interact with their internal knowledge. Instead of relying on public search engines or general-purpose AI models that may hallucinate or use irrelevant information, AgentOS allows users to build secure, domain-specific knowledge workspaces from their own documents. Users can organize documents into projects and collections, upload PDFs, technical documentation, research papers, company policies, manuals, or reports, and selectively choose which collections should be available for answering each query. This ensures every response is grounded only in trusted sources.