Tag
Eve is a framework for building durable, production-ready AI agents with built-in observability, introspection, and self-improvement capabilities, designed to work seamlessly with Next.js and Vercel deployments.
fast-rlm is an open-source Python tool that allows LLMs to operate within an RLM harness for recursive subagent calls, with features like spend limits and live log streaming.
KDA (Kernel Design Agents) is an open-source agent-centric workflow from MIT HAN Lab for using coding agents to research, implement, verify, and iterate on performance-sensitive CUDA kernel tasks. It helped Databricks achieve rank #1 on NVIDIA's SOL-ExecBench leaderboard.
The University of Hong Kong Data Intelligence Lab has open-sourced the lightweight agent framework OpenHarness and its built-in agent Ohmo, providing core features like tool calling, memory, multi-agent coordination, and support for platforms like Feishu and Slack.
The author shares an open-source workspace architecture that structurally prevents AI agents from exfiltrating private data by enforcing human-gated outbound actions and isolating the engine from the data repository.
Deep Agents introduces dynamic subagents that use programmatic orchestration via code scripts instead of tool calls, enabling reliable scaling and complex workflows. The feature integrates with a QuickJS code interpreter for lightweight execution.
A tool for remotely harnessing and managing AI agents.
Descripción detallada del sistema de memoria OpenClaw para agentes de IA, incluyendo la estructura completa del workspace, archivos de arranque, estado, tiempo, semántica y búsqueda con QMD.
Vercel released Eve, an open-source framework for building and scaling AI agents using a filesystem-first approach, treating agents as directories of files. The framework provides durable sessions, sandboxing, approvals, tracing, and evals out of the box.
Vercel launched Eve, an agent framework with built-in observability, debugging, durable execution, and sandboxed compute, aiming to simplify production agent development.
Alex, a new LangChain team member, published an article explaining how Deep Agents uses prompt caching to reduce API costs.
EGG is an expert-guided agent framework that decomposes GPU kernel generation into algorithmic structure design and hardware-specific tuning, using a stage-aware multi-agent collaboration mechanism. It achieves a 2.13x average speedup over PyTorch on KernelBench and real-world workloads.
This paper proposes an LLM-based system to automate email dispatching to students' WhatsApp groups, reducing manual effort and errors in organizations.
ActiveGraph announces two new papers on agent memory (LongMemEval) and self-improvement regimes, along with reference agents, pack templates, and upcoming meetups in Seattle and San Francisco.
NVIDIA introduces the Agent Toolkit, an open modular foundation with models, tools, skills, and a secure runtime to help businesses build specialized, trustworthy AI agents for various industries.
Self-Harness introduces a new paradigm where LLM-based agents iteratively improve their own operating harness by mining model-specific weaknesses, proposing harness modifications, and validating them through regression testing, achieving substantial performance gains on Terminal-Bench-2.0 across multiple base models.
A developer introduces agent-rigor, an open-source framework that enforces runtime discipline and traditional SDLC mechanics into AI coding assistants to prevent common agent failures like scope creep and fix-forward loops.
TokenArch Lanterns is a framework for exploring and developing standards for autonomous agents.
A developer presents a tier list of AI agent frameworks for local autonomous workflows, ranking OpenClaw as S-tier and Gemini Spark as A-tier, while criticizing cloud-locked wrappers for requiring excessive manual approvals.
Firecrawl launches Keyless mode, allowing free trials without an API Key. It supports real-time web scraping, interactions, and PDF parsing, with 1000 free Credits monthly. Suitable for Agent frameworks like Claude Code and Cursor.