AI-Agents provides a flexible, modular platform for creating autonomous AI-driven agents. Developers can define agent objectives, chain tasks, and incorporate memory modules to store and retrieve contextual information across sessions. The framework supports integration with leading LLMs via API keys, enabling agents to generate, evaluate, and revise outputs. Customizable tool and plugin support allows agents to interact with external services like web scraping, database queries, and reporting tools. Through clear abstractions for planning, execution, and feedback loops, AI-Agents accelerates prototyping and deployment of intelligent automation workflows.

AgenticIR (Agentic Information Retrieval) provides a modular framework where LLM-powered agents autonomously plan and execute IR workflows. It enables the definition of agent roles — such as query generator, document retriever, and summarizer — running in customizable sequences. Agents can fetch raw text, refine queries based on intermediate results, and merge extracted passages into concise summaries. The framework supports multi-step pipelines including iterative web search, API-based data ingestion, and local document parsing. Developers can adjust agent parameters, plug in different LLMs, and fine-tune behavior policies. AgenticIR also offers logging, error handling, and parallel agent execution to accelerate large-scale information gathering. With a minimal code setup, researchers and engineers can prototype and deploy autonomous retrieval systems.

Canny is a complete customer feedback platform that allows you to centralize, analyze, and prioritize feedback from various sources. It enables you to build roadmaps and share updates with your audience. With features like feedback collection, analysis, prioritization, and sharing, Canny helps you build better products by understanding and acting on customer needs. It offers integrations with tools like Jira, Salesforce, and Hubspot to connect feedback with the revenue impact and ensure your team's workflow is seamless.

Langtrace offers a comprehensive suite of features that helps developers monitor and enhance their large language model applications. It utilizes OpenTelemetry standards for compatibility, allowing the collection of traces from various sources and offering insights into performance metrics. This tool assists in identifying trends, anomalies, and areas for improvement, thereby making applications more efficient and reliable. It empowers teams to establish automated evaluations and feedback loops, significantly streamlining the development and enhancement processes of LLM applications.

ManasAI is a Python-based framework that enables the creation of autonomous AI agents with built-in state and modular components. It offers core abstractions for agent reasoning, short-term and long-term memory, external tool and API integrations, message-driven event handling, and multi-agent orchestration. Agents can be configured to manage context, execute tasks, handle retries, and gather feedback. Its pluggable architecture allows developers to tailor memory backends, tools, and orchestrators to specific workflows, making it ideal for prototyping chatbots, digital workers, and automated pipelines that require persistent context and complex interactions.

Meta-Agent-with-More-Agents is an extensible open-source framework that implements a meta agent architecture allowing multiple specialized sub-agents to collaborate on complex tasks. It leverages LangChain for agent orchestration and OpenAI APIs for natural language processing. Developers can define custom agents for tasks like data extraction, sentiment analysis, decision-making, or content generation. The meta agent coordinates task decomposition, dispatches objectives to appropriate agents, gathers their outputs, and iteratively refines results via feedback loops. Its modular design supports parallel processing, logging, and error handling. Ideal for automating multi-step workflows, research pipelines, and dynamic decision support systems, it simplifies building robust distributed AI systems by abstracting inter-agent communication and lifecycle management.

SCOUT-2 provides a modular architecture for building autonomous agents powered by large language models. It includes goal decomposition, task planning, an execution engine, and a feedback-driven reflection module. Developers define a top-level objective, and SCOUT-2 automatically generates a task tree, dispatches worker agents for execution, monitors progress, and refines tasks based on outcomes. It integrates with OpenAI APIs and can be extended with custom prompts and templates to support a wide range of workflows.

Pentagi is a no-code AI agent platform that lets you create, train, and deploy intelligent conversational agents for various business scenarios. Using its visual flow builder, you define intents, entities, and response actions. Integrations with external APIs enable dynamic data retrieval and automated task execution. Deploy your agents on web chat widgets, messaging apps, or mobile SDKs, then monitor performance through a built-in analytics dashboard to optimize conversations and agent effectiveness.