Live intelligence

Latest AI updates

22 updates
Products

MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily

MiniMax has open-sourced MCode Stack, a collection of 17 SKILL.md agent skills and 5 checklists used by its MiniMax Code team, released under the MIT license on October 28, 2026. The stack focuses on harness engineering, including planning, context management, code review, and long-session handling, and installs into MiniMax Code or Claude Code. No benchmarks or eval results are published, so it serves as a practical playbook rather than proven performance. The skills are plain Markdown and compatible with agents supporting the SKILL.md format.

MiniMax Codeagent workflowsopen-source AI tools
Research Editor selected

Microsoft Research Open-Sources Agensh, an Orchestrator-Free Multi-Agent Harness Tested at 1,024 Agents

Microsoft Research has open-sourced Agensh (MIT), a decentralized harness for large teams of coding agents that removes the central orchestrator. Each worker runs the same five-step prompt-based loop, claims sub-tasks, and shares state through a Gitea repo, a Mattermost channel and a typed context board. On the five hardest ProgramBench tasks, more agents improved scores: with GPT-5.6-sol the mean rose from 19.31% with 1 agent to 28.78% with 128. The README reports GPT-6.1-sol reaching a 79.59%

Why it matters: It documents a concrete open-source multi-agent architecture with published scaling behavior and benchmarks, giving agent builders a reproducible alternative to orchestrator-worker designs.

Microsoft Researchmulti-agent systemscoding agents
Research

Study: Coding-Agent Harness Choice Barely Affects Pass Rates, but Can Triple Cost

A controlled study compared coding-agent harnesses such as Claude Code, OpenCode and mini-SWE-agent and found that switching between them changes pass rates little more than simply rerunning the same setup. Cost per task, however, can triple, with the system prompt resent at every step cited as the main driver.

coding agentsagent evaluationLLM inference cost
Products

Vercel Open-Sources durable-harness for Crash-Proof Coding Agents

Vercel released durable-harness, an Apache-2.0 TypeScript package that wraps existing coding agent harnesses (Pi, OpenCode, fx, Claude Code, Codex) and stores each session in a durable log via its Workflow SDK World. It records intent before model and tool calls and outcomes after, so a crashed function's turn can resume on a new function without re-running finished calls or double-billing tokens. It runs on Vercel Functions and Queues, locally, or self-hosted on Node.js 22+ with Postgres. The p

Vercelcoding agentsdurable execution