New in week 43

Rust library for LLM applications with agents, tool calling, streaming and 20+ model providers, plus a terminal coding agent.

Open-source framework that routes each user query to one of several AI agents, with Python, TypeScript and Swift runtimes.

Rails framework for building AI agents as controllers, with provider gems for OpenAI, Anthropic, Ollama and more.

Open-source Python framework for AI agents that cooperate on tasks, with human-in-the-loop workflows and multi-agent patterns.

AI application runtime framework for backends with structured outputs, observable actions, MCP capabilities and recoverable workflows.

Elixir framework for autonomous agents with state, actions, signals and directives, running on OTP supervision.

Python agent framework from Alibaba that lets the model drive tool use, with team pipelines, MCP, agent skills, A2A, memory and tracing.

Java framework for distributed, long-running agents with typed event streams, permission gating, middleware and subagents.

Python runtime for agent apps with tool sandboxing and streaming agent APIs; archived, with features moved to AgentScope 2.0.

Open-source Python evaluation framework with ready-made and custom graders for scoring AI agent quality and producing reward signals.

Python multi-agent framework with PEER and DOE collaboration patterns and configurable LLM vendors such as Qwen, DeepSeek and OpenAI.

Library for LLM post-training (SFT, DPO, GRPO and agentic RL) and classic RL, with evolutionary hyperparameter optimization.

Python framework and runtime for building agents, serving them over a REST API and MCP server, and managing them from a web control plane.

SDK for building durable, responsive services, including agentic AI services, that cluster automatically and deploy to any infrastructure.

Java framework for agentic, workflow and multi-agent AI apps, with graph workflows, MCP and A2A support.

Open-source framework that builds, evaluates and self-improves multi-agent LLM workflows from a goal.

Python SDK that runs the Claude Code agent loop inside your own program, with custom tools and hooks written as Python functions.

TypeScript SDK that gives programs Claude Code's built-in tools for reading, editing and running code, installed from npm.

Reliability layer for tool calling with self-hosted LLMs, offered as a proxy, a workflow runner and middleware.

Python framework that models an application as a state machine, with a trace UI and persisted state.

Lightweight Python framework and starting template for agents that let the model choose its own approach to each task.

Java runtime for AI agents that streams tokens and tool events over WebSocket, SSE or gRPC, with human approvals.

Python SDK for deploying agents to Amazon Bedrock AgentCore, a managed runtime with memory, gateway, tools and observability.

DSPy-style toolkit for typed LLM signatures, agents and flows, TypeScript-first with Python, Java, C++, Go and Rust libraries.

Typed Python toolkit for composing classic and agentic retrieval-augmented generation pipelines with pluggable LLMs and stores.

Open-source platform for voice agents that place and answer phone calls through Twilio or Plivo with pluggable speech and LLM providers.

Rust framework with an agent harness, typed task graphs and streaming indexing and RAG pipelines for LLM applications.

SDK for browser agents with act, observe and extract calls, used from TypeScript and Python to automate sites and pull out structured data.

Python agent runtime with an SDK for building your own agent, and an app that adds plugins and channel integrations.

Open-source Python framework for multi-agent systems: agent societies, memory, RAG, code interpreters, synthetic data and large-scale simulation.

Python runtime and framework for long-running agents, with durable sessions, approvals, spend caps and multi-agent collaboration.

Cross-platform C++ DAG framework with a Python version, for running task graphs with no third-party dependencies.

TypeScript SDK for persistent AI agents on Cloudflare Durable Objects, with state sync, scheduling and MCP support.

Go framework for LLM applications with chat-model agents, multi-agent coordination, graph workflows and human-in-the-loop resume.

Coinbase toolkit that gives AI agents a crypto wallet and onchain actions, framework- and wallet-agnostic.

Open-source SDK that connects AI agents to app front ends with chat UI, generative UI, shared state and human approvals; creator of the AG-UI protocol.

Open-source Python framework for multi-agent workflows, with role-based Crews and event-driven Flows.

Ruby AI framework with one API for chat, tools, agents, streaming, embeddings and Rails integration across many providers.

Python framework for LLM agents that run as durable Dapr workflows, with retries, Kubernetes deployment and human-in-the-loop hooks.

Low-code Python framework for YAML-defined agents and multi-agent Cogs, with personas, prompt templates and memory nodes.

Python library that turns files in S3, GCS and Azure into versioned, typed datasets for pipelines and agents.

Open-source Python framework from deepset for modular pipelines and agent workflows covering retrieval, tool use and generation.

Minimal TypeScript agent harness with an agent runtime, multi-provider LLM API, terminal UI and coding agent CLI that users extend themselves.

Lightweight Python framework for composing AI agents and tools as small, typed pieces built on Instructor and Pydantic.

TypeScript framework and product stack for autonomous agents, with a plugin system, persistent memory, a CLI, an app and cloud services.

JVM framework for agentic flows that plan toward goals, mixing LLM calls with code and domain models, usable from Kotlin or Java.

Python framework for customer-facing conversational agents that narrows the prompt context each turn using rules, knowledge and tools you define.

CLI-first Python agent framework and coding agent with MCP, A2A and Agent Skills support, live streaming and human input.

Python library of 35 agentic AI architectures with one run() interface, built on LangGraph and multiple LLM providers.

Python library for autonomous agents that run scheduled tasks and exchange messages on the Fetch.ai network.