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
TeleAI-UAGI/telemem
TeleMem is a memory management layer for LLM agents, published by TeleAI as a Python package on PyPI and accompanied by a technical report on arXiv. Its stated design goal is API compatibility with Mem0: the module can be imported under the Mem0 name, and the add and search calls take the same arguments and return the same result structure, so existing code that depends on Mem0 keeps working after the swap. On top of that interface the project adds a context-aware extraction mechanism aimed at multi-turn dialogue, and it builds separate memory profiles per character or persona, which targets role-play assistants, companion applications and non-player characters that must not share facts between identities. Beyond text, TeleMem implements a video pipeline that extracts frames, generates captions for them and stores the results in a vector database, after which an agent can retrieve and reason over video content through a ReAct-style multi-step question answering loop. The default deployment runs entirely on local hardware with Qwen models and a FAISS index, so no external service is required, and the project also ships configurations for Ollama, DeepSeek and Kimi plus examples for LangChain and LlamaIndex. TeleMem exposes its functionality as an MCP server with eight memory tools, built on the official MCP Python SDK and listed in the MCP registry, so the memory store can be attached to any MCP-capable agent runtime without writing integration code. Evaluation material includes a LongMemEval harness with baselines. The audience is developers who already build agents or chatbots and need persistent recall, character consistency across sessions or multimodal memory without moving user data to a hosted memory service.
https://github.com/TeleAI-UAGI/telemem
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.