mlx-engine v1.8.5 dramatically improves performance for repeated, long-context agentic workflows by checkpointing your KV cache.
Optimizing Agentic Workflows using Meta-tools
Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations,...
Awni Hannun on Twitter / X
The latest mlx-lm is out and it has continuous batching with mlx_lm.server! Added by @angeloskath Check-out the video of 4 simultaneous requests running with Qwen3 30B on the same M2 Ultra: https://t.co/o9sFC3k4DN— Awni Hannun (@awnihannun) December 3, 2025
shepherd-agents/shepherd
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents
kvcache-ai/AgentENV
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Inngest - Durable Execution for Workflows & AI
Build reliable background jobs, workflows, and AI agents without extra infrastructure. Automatic retries, flow control, and step-level observability.
Code execution with MCP: building more efficient AI agents
Learn how code execution with the Model Context Protocol enables agents to handle more tools while using fewer tokens, reducing context overhead by up to 98.7%.
raullenchai/Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
raullenchai/Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
Liquid AI on Twitter / X
Today, we release LFM2.5-350M. Agentic loops at 350M parameters.A 350M model trained for reliable data extraction and tool use, where models at this scale typically struggle.<500MB when quantized, built for environments where compute, memory, and latency are constrained.🧵 pic.twitter.com/zZPKzcCwH9— Liquid AI (@liquidai) March 31, 2026
Introducing LFM2: The Fastest On-Device Foundation Models on the Market | Liquid AI
Today, we release LFM2, a new class of Liquid Foundation Models (LFMs) that sets a new standard in quality, speed, and memory efficiency for on-device deployment. Built on a hybrid architecture, LFM2 delivers 200% faster decode and prefill performance than Qwen3 and Gemma 3 on CPU. It also significantly outperforms models in each size class on instruction-following and function calling—the core capabilities that make LLMs reliable for building AI agents.
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Large Language Model (LLM) agents have been widely adopted in modern software development workflows. SWE-bench [13] and related works [23, 24, 22, 25, 15] establish the task of issue resolution as a de-facto standard for assessing their capability and usefulness. In this setting, an agent is given an entire codebase, a task description (e.g., a bug report or feature request) in natural language and is instructed to produce a code patch that resolves the issue and passes the repository’s test suite. These benchmarks have been instrumental in demonstrating both the substantial potential and the persistent limitations of current models as SWE agents.
NVIDIA Rubin CPX Accelerates Inference Performance and Efficiency for 1M+ Token Context Workloads | NVIDIA Technical Blog
Inference has emerged as the new frontier of complexity in AI. Modern models are evolving into agentic systems capable of multi-step reasoning, persistent memory, and long-horizon context—enabling…
Open-Source Agentic Inference Benchmark | InferenceX
Compare AgentX, InferenceX's long-context, multi-turn coding scenario, with fixed-sequence AI inference across chips and frameworks. Public NVIDIA and AMD runs update when configurations change.
Vercel Workflow
Build durable, reliable, and observable applications and AI agents with the Workflow Development Kit (WDK).
Staff engineer shows AI spec-driven development workflow