Open-source alternatives to Superagent

Plano is an AI agent orchestrator and LLM gateway proxy that unifies access to multiple AI providers through a single interoperable interface. It functions as a model routing engine that decouples applications from specific vendors using semantic aliases, allowing traffic to be shifted between providers without modifying application code. The system distinguishes itself with intent-based agent routing, which directs prompts to specialized agents based on semantic analysis. It features an interceptor-based filter chain system that acts as guardrail middleware to enforce safety policies, rewrit

promptfoo is an evaluation framework for measuring the performance of large language model prompts, agents, and retrieval augmented generation pipelines. It provides a suite of tools for conducting comparative benchmarking and executing automated quality and security regressions. The system features a benchmarking suite for running identical prompts across different model providers to compare output quality side-by-side. It also includes a dedicated red teaming tool for identifying security vulnerabilities and prompt injection risks through automated penetration testing. The framework suppor

RagaAI-Catalyst is a suite of software implementation tools providing an SDK, dashboard, and platform for monitoring, debugging, red-teaming, and evaluating agentic AI workflows. It serves as an observability framework for tracing the execution paths of large language models and multi-agent systems. The project distinguishes itself through a security suite for automated red-teaming and vulnerability scanning to detect biases, alongside a centralized prompt registry that decouples templates from application code. It further provides an evaluation platform that combines synthetic data generatio

The agent-governance-toolkit is a framework for enforcing security policies, managing zero-trust identities, and sandboxing the execution of autonomous AI agents. It provides a governance layer designed to control the behavior of agents through the use of a security policy engine, cryptographic identity management, and a runtime execution sandbox. The project distinguishes itself through a multi-tier privilege ring system and a cryptographic identity mesh that secures communication between autonomous entities. It implements a decay-based trust scoring mechanism to track entity reliability and

AI-Infra-Guard is a security scanning platform designed to detect vulnerabilities across large language model deployments, AI agent skills, and the underlying infrastructure. It functions as a security toolset for auditing source code, evaluating model robustness, and identifying insecure network configurations. The project provides a red teaming framework that uses curated attack datasets to test for jailbreak vulnerabilities and prompt injections. It also includes an infrastructure auditor that employs network fingerprinting and asset discovery to match running components against known comm

SkillSpector is a security scanner designed to detect vulnerabilities and malicious patterns in AI agent plugins and extensions before they are installed. It functions as a runtime guardrail that calculates numeric risk scores and assigns severity labels to provide installation recommendations or block risky external extensions. The project distinguishes itself by using language models to perform semantic code analysis, evaluating code intent and context to reduce false positives. It also employs fingerprint-based issue suppression to track and ignore previously accepted risks across repeated

Promptfoo is an evaluation framework designed for testing, benchmarking, and red-teaming language models and agentic workflows. It provides a unified environment to run prompts against multiple providers, allowing developers to systematically validate model outputs against objective assertions, semantic similarity metrics, and custom grading rubrics. The platform distinguishes itself through a provider-agnostic execution layer and a stateful orchestrator capable of simulating multi-turn conversations and complex tool-use trajectories. It includes a dedicated adversarial mutation pipeline that

ruby_llm is an LLM integration framework and AI agent orchestrator designed to connect applications to multiple large language model providers through a unified interface. It serves as a toolkit for building autonomous assistants with custom personas, managing structured output via JSON schemas, and implementing vector embedding engines for semantic search. The project distinguishes itself as an observability suite and multimodal toolkit. It provides specialized capabilities for tracking token usage, calculating model costs, and tracing workflows via OpenTelemetry, while supporting the proces

Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs. The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b

Deepeval is a framework for testing and evaluating large language model applications. It provides a suite of tools for executing automated regression tests, validating model output quality against defined standards, and tracing the execution of complex agent workflows. By integrating these capabilities into development pipelines, the platform ensures consistent performance and reliability throughout the software lifecycle. The platform distinguishes itself through its focus on programmatic validation and observability. It utilizes secondary language models to score output quality and employs

Presidio is a PII detection and anonymization framework designed to identify and mask personally identifiable information in text. It functions as a PII recognition pipeline and a data masking engine, using a combination of machine learning, regular expressions, and rule-based logic to locate sensitive entities. The system acts as an NER model orchestrator, allowing for the integration of external named entity recognition models and PII detectors to support multi-language privacy scrubbing. It employs a plugin-based recognizer architecture that can be extended with custom recognizers, deny-li

Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents through defined communication patterns and handoffs. It functions as a system for managing agent swarms, providing an API gateway to expose these coordinated collectives as production-ready HTTP endpoints. The project distinguishes itself through its Model Context Protocol integration layer, which connects agents to external data sources and capabilities. It implements specialized orchestration patterns, such as the orchestrator-worker model and role-based delegation, to tran

Danswer is an LLM application framework and RAG engine that provides a self-hosted interface for connecting large language models to private data. It serves as an enterprise AI chat interface and agent orchestrator, enabling the creation of specialized assistants with custom instructions and knowledge bases. The platform differentiates itself through an observability dashboard for tracking query history and token consumption, as well as a white-labeled interface for customized branding. It includes a multi-step research workflow for producing long-form reports and a sandboxed environment for

Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut

Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language models. It functions as a non-intrusive layer that intercepts outbound model requests to automatically capture interaction history and execution traces, ensuring that agents maintain continuity across sessions without requiring modifications to existing application logic. The platform distinguishes itself through a dual-model storage architecture that maintains information as both structured relational primitives for precise fact retrieval and rolling narrative summaries for situ

dbt-core is a command-line framework for transforming data within a warehouse using modular SQL and version control. It functions as a data transformation engine that enables users to define data structures and business logic through declarative configuration files, which the system then compiles into executable code. By managing complex data dependencies through a directed acyclic graph, it ensures that transformation tasks execute in the correct order while maintaining a manifest-driven state to track lineage and execution history. The project distinguishes itself through an adapter-based d

PurpleLlama is a collection of security components and toolkits designed for large language models. It provides specialized systems including a code security scanner, a content moderation system, a prompt injection firewall, and a security assessment toolkit. The project enables the identification and blocking of jailbreaking attempts and malicious prompts during model inference. It includes capabilities for detecting violating content across multiple languages and modalities and scanning generated code for vulnerabilities to prevent the execution of insecure commands. The framework further

Agents is an open-source software development kit for building, securing, and deploying multichannel conversational AI assistants across enterprise productivity platforms and web interfaces. It functions as a comprehensive framework that enables developers to operate full-stack conversational assistants across multiple messaging channels simultaneously from a single codebase, while connecting agents to large language models and custom orchestration logic without vendor lock-in. The architecture features an adapter-based channel multiplexing system that routes unified agent messages to diverse

This project is an educational and research platform designed to simulate security vulnerabilities within AI-integrated systems and Model Context Protocol implementations. It provides a controlled environment where users can practice identifying and mitigating common attack vectors, such as prompt injection and unauthorized code execution, by interacting with intentionally insecure tools and protocol configurations. The platform distinguishes itself by offering a dedicated laboratory for auditing Model Context Protocol integrations. It exposes server-side functions as discoverable tools and p

L1B3RT4S is an adversarial machine learning toolkit designed for red teaming and evaluating the robustness of large language models. It provides a research framework for investigating how safety alignment mechanisms and content moderation systems respond to sophisticated input strategies. The project focuses on identifying vulnerabilities in model guardrails by employing techniques such as adversarial narrative framing, dynamic context injection, and latent space steering. It utilizes multi-agent prompt decomposition and recursive text transformation to analyze how structural changes to input

This project is a Llama Stack agentic framework and orchestrator used to build autonomous AI applications. It coordinates model inference and tool execution to decompose complex goals into multi-step reasoning chains and continuous inference loops. The framework incorporates a dedicated safety guardrail system that filters model inputs and outputs through safety models to enforce system-level content restrictions. It also includes a tool integration layer that maps model-generated function requests to external runtime definitions to execute actions beyond text generation. The system provides

ClaraVerse is a self-hosted orchestration platform for deploying and managing local language models, autonomous agents, and automated workflows on private infrastructure. It functions as a containerized backend manager that orchestrates services, databases, and model providers within local containers to maintain data sovereignty. The platform features a visual workflow builder with a drag-and-drop interface for designing complex parallel task sequences. It utilizes a multi-model abstraction layer to normalize interactions across diverse local and remote AI endpoints and includes a retrieval a

PyRIT is an AI vulnerability assessment tool and security scanner designed to detect risks in large language model applications. It functions as a generative AI red teaming framework used to simulate adversarial attacks and identify weaknesses in system guardrails. The tool automates AI risk assessment by scanning generative AI components for security vulnerabilities. It utilizes automated testing and analysis to identify security gaps and prevent potential exploits through a consistent, repeatable process. The system incorporates asynchronous model orchestration to compare security postures

OpenChat is an AI chatbot management platform used for building, deploying, and managing custom agents powered by large language models. It serves as an omnichannel customer support suite that integrates language model automation with communication channels including email, SMS, social media, and voice. The platform features a retrieval-augmented generation knowledge base integrator that ingests documents, websites, and codebases to provide context-aware responses. It includes a dedicated privacy layer for the detection and removal of sensitive personal and health information to maintain regu

k8sgpt is a suite of Kubernetes-focused tools designed for AI-powered debugging, cluster diagnostics, and self-healing. It functions as an automated analyzer and debugger that uses large language models to explain cluster errors, suggest remediation steps, and identify resource failures. The project distinguishes itself through an extensible analysis framework that supports custom diagnostic plugins and a Model Context Protocol server, which exposes cluster diagnostics as tools for AI assistants. It includes a self-healing agent capable of automatically generating and applying fixes for detec