spring-ai-agent-utils

Mem0 stores user, session, and agent state so assistants, support bots, and automated systems can recall preferences and prior interactions. Developers can integrate it through Python or JavaScript libraries, a CLI, a self-hosted server, or the managed platform. Its core workflow depends on an LLM and an embedding model, and some managed-platform optimizations are not included in the open-source SDK.

smolagents offers a compact Python framework for code-writing agents, conventional tool-calling agents, and multi-agent hierarchies, with support for different model providers and Hub sharing. Its CodeAgent expresses actions as Python snippets. Since those snippets are executed, untrusted workloads should use a sandboxed backend; the local Python executor is explicitly not a security boundary.

SkillOpt treats a skill document as the trainable state of an otherwise frozen agent. An optimizer model converts scored trajectories into bounded add, delete, or replace edits, and a candidate is accepted only when it strictly improves a held-out validation score. The resulting best_skill.md can be deployed without changing model weights or adding extra model calls at inference time, giving researchers and engineering teams a controlled way to improve reusable agent instructions.

SWE-smith creates Docker execution environments from GitHub repositories, synthesizes tasks such as file localization and program repair, filters instances that break one or more tests, and generates issue text. The resulting tasks and trajectories can support SWE-agent training or evaluation. It requires Docker and was developed for Ubuntu 22.04; Windows and macOS are not planned targets.