Most AI agents are optimized to complete a task. openJiuwen's WorkSwarm is pushing toward something more ambitious: agents that improve themselves through real work. Three things that make it different 👇 1.⁠ ⁠Dual-Dimension RSI A continuous self-improvement loop — Evaluate → Analyze → Propose → Execute → Adopt — that improves both how the agent works (prompts, skills, tools) and what it delivers (papers, code, artifacts). 2.⁠ ⁠Persistent Sessions Keeps roles, decisions, and boundaries intact across hundreds of turns. In one test: 5 people, 189 turns, 8/8 cross-role conflicts caught. 3.⁠ ⁠Compute Affinity Optimizes resource usage — 22.8% lower HBM peak, 14.36% higher KV cache hit rate — making repeated optimization more efficient. Open source under Apache 2.0. GitHub 👉 #AI# #Agent# #openJiuwen# #WorkSwarm#

Introducing Ito: The AI Code Reviewer That Actually Runs Your Code Most AI code reviewers only read your code. Ito actually runs it. Ito is an AI-powered code review and QA agent that tests every pull request inside a real application environment. It analyzes what changed, creates a targeted test plan, runs the affected flows, and finds bugs that may never show up in a normal code review. 🔗 Key Features: • Runs your app: Tests actual application behavior, not just code diffs. • Automatic test plans: Generates targeted tests based on each PR. • Finds runtime bugs: Catches issues across APIs, authentication, databases, integrations, and user flows. • Real evidence: Provides screenshots, videos, logs, reproduction steps, and relevant code references. • Automatic retesting: Verifies whether a pushed fix actually resolves the issue. • No test scripts required: Ito handles testing without maintaining large end-to-end test suites. Ito works like an AI QA engineer inside every pull request. Instead of telling you what might break, it tests your software to find out what actually breaks.