All AI agent resources

A browser-grounded social research agent that lets Jev select bounded operations, uses the socai CLI in the user's Chrome session, and generates source-linked reports.

jevme is a voice-controlled macOS agent that uses accessibility controls to operate apps, executes commands as the user speaks, and learns reusable tasks from demonstrations.

Julep builds durable, composable AI agents as workflows that can resume after failures, retry safely, and expose step-by-step execution.

A Kubernetes operator for deploying and managing AI agent runtimes, with bounded self-healing that keeps LLMs out of the cluster's workload write path.

An open-source replay-based evaluation toolkit for AI agents that records or imports production traces as sessions and reruns them against model, prompt, or code changes.

kith gives multi-agent systems relationship memory: agents record scoped observations and derive trust, reliability, sentiment, and capability views with provenance.

An autonomous multi-agent coding orchestrator that runs coding agents through work cycles with independent verification.

A self-hosted multi-cluster Kubernetes dashboard with an AI operations agent that connects language models to live clusters through MCP.

LangChain is a framework enabling context-aware reasoning applications with integrated libraries, templates, and developer tools

LangChain JS is a framework for developing applications powered by language models, enabling context-aware and reasoning-based applications through composable tools and off-the-shelf chains, with seamless integration with the LangChain Python package

Langchain features VectorDBQAChain, which integrates LLMs and vector databases into agent tools for enhanced question-answering capabilities by leveraging data ingested into vector stores

Langchain integrates various providers like Anthropic, AWS, and OpenAI, and offers tools for components such as LLMs, chat models, and data analysis, supporting functionalities from Alpha Vantage to YouTube

Trace agent runs, manage prompts and evaluate outputs in an AI engineering platform.

Build stateful agent workflows with explicit control over steps, persistence and human review.

LangGraph.js is a TypeScript and JavaScript library enabling the development of stateful, multi-actor applications with LLMs, featuring capabilities to construct cyclic coordination across multiple computation steps for complex agent-like behaviors, with support for conditional edges and cycles, not limited to DAGs, and extensive documentation with examples on implementation

LangServe facilitates the deployment of LangChain runnables and chains as a REST API, providing features like automatic schema inference, efficient endpoints, and a playground page, with plans for a hosted version for one-click deployments

LangSmith provides tools for debugging, testing, evaluating, and monitoring LLM applications, integrating seamlessly with LangChain for comprehensive AI agent observability

LiteLLM has added support for the OpenAI Assistants API, enabling seamless integration of stateful operations and automatic RAG pipelines into existing chatbots