mudler/LocalAI
LocalAI is an open-source AI engine that enables running various AI models (LLMs, vision, voice, image, video) on any hardware, including CPU-only systems, with a composable and extensible architec...
Awesome AI Agents › LLM Framework Tools
ServiceNow/TapeAgents
TapeAgents is a comprehensive framework designed to facilitate all stages of the development lifecycle of Large Language Model (LLM) Agents. It leverages a unique structured, replayable log called a "Tape" that records the entire agent session, enabling detailed reasoning and interaction tracking. The agent processes this tape along with LLM outputs to generate new thoughts, actions, and control flow steps, which are appended back to the tape. The environment responds to these actions by adding observation steps, creating a dynamic and interactive development process. The framework supports building agents in various configurations, including low-level state machines, high-level multi-agent teams, or mono-agents guided by multiple prompts. This flexibility allows developers to tailor agents to specific needs and complexities. TapeAgents also offers robust debugging tools through the TapeAgent studio and TapeBrowser apps, enhancing the development experience by allowing developers to inspect and modify the agent's behavior interactively. Serving agents with response streaming is another key feature, providing real-time interaction capabilities. Additionally, the framework supports optimization of agent configurations by utilizing successful tapes and fine-tuning the LLM with revised tapes, improving agent performance over time. TapeAgents is designed for ultimate flexibility, giving developers full control over the agent's tape and actions. It allows for prompt and team structure modifications with the ability to resume debugging sessions seamlessly. The framework's metadata structure links tapes, steps, LLM calls, and agent configurations, facilitating efficient optimization and management. The project includes extensive examples demonstrating various use cases such as planning, web searching, code interpretation, multi-agent team configurations, and fine-tuning for specific tasks like math problem-solving. Installation is straightforward via pip, with options for additional dependencies for converters and fine-tuning. The project is well-documented, with tutorials, technical reports, and active contact points for support. TapeAgents draws inspiration from notable frameworks like LangGraph, AutoGen, AIWaves Agents, and DSPy, positioning itself as a powerful tool for LLM agent development.
https://github.com/ServiceNow/TapeAgents
Also in LLM Framework Tools
langfuse/langfuse
Langfuse is an open source LLM engineering platform that enables collaborative development, monitoring, evaluation, and debugging of AI applications with comprehensive observability, prompt management, and integration features.
567-labs/instructor
Instructor is a popular Python library that simplifies working with structured outputs from large language models by providing validation, retries, and streaming support across multiple LLM providers.
TEN-framework/ten-framework
TEN Framework is a real-time, distributed, cloud-edge collaborative multimodal AI agent framework supporting multiple programming languages for building high-performance AI applications.
google/adk-samples
A collection of sample agents built with the Agent Development Kit (ADK) to accelerate development of conversational and multi-agent workflows, designed for customization and integration with Google Cloud services.
truefoundry/cognita
Cognita is an open-source, modular, and production-ready RAG framework by TrueFoundry that simplifies building, customizing, and deploying scalable Retrieval Augmented Generation applications with a no-code UI and extensive integration features.
lemony-ai/cascadeflow
In-process Python and TypeScript library that cascades model calls inside the agent loop, routing each query or tool call between small and flagship models by quality, cost, latency and budget.
shroominic/codeinterpreter-api
An open-source API that implements the ChatGPT Code Interpreter for sandboxed Python code execution, enabling data analysis, visualization, and interactive AI-driven computational tasks with local execution and scalable production deployment.