AI Coding Live News

ByteDance Releases DeerFlow 2.0: Ground-Up Rewrite of 83K-Star Long-Horizon SuperAgent Harness

ByteDance launched DeerFlow 2.0.0, completing a ground-up rewrite of its 83k-star open-source agent harness with 182 merged PRs. Built around a SuperAgent architecture, DeerFlow 2.0 orchestrates sub-agents, persistent memory, and sandboxed execution with extensible tools. It introduces self-updating SOUL memory, user-owned IM channel integrations (Feishu, DingTalk, WeChat, Slack, Discord, Telegram), Docker DooD sandbox protection, and deep integration with BytePlus InfoQuest crawling technology for robust multi-hour autonomous execution.

ByteDance Releases DeerFlow 2.0: Ground-Up Rewrite of 83K-Star Long-Horizon SuperAgent Harness

Key Takeaways

  • Full architectural rewrite: migrated from rigid workflows to a SuperAgent harness orchestrating sub-agents, memory, and sandboxes
  • Evolving agent souls: agents can modify and persist their own SOUL.md and YAML configs across chats with strict user isolation
  • Universal IM gateway: native support for Feishu/Lark, DingTalk, WeChat/WeCom, Slack, Discord, and Telegram integrations
  • Enterprise-grade sandbox: DooD Docker isolation with automated zip-bomb protection and sensitive MCP credential masking
  • Production observability: Langfuse distributed tracing with parent-child attribution and thread-indexed O(1) query acceleration
Read full story

Instar open-sources persistent Claude Code agents with memory and cron

@DanKornas highlighted JKHeadley/instar, an open-source framework that pairs real Claude Code processes with persistent SQLite memory, cron jobs, and messaging so agents keep working across sessions. Features include SQLite/FTS5/rolling summaries with context re-injection, priority- and quota-aware scheduled work, Telegram/WhatsApp/iMessage, per-session tools/hooks/skills/MCP, plus behavioral hooks and external-operation gates. MIT.

Key Takeaways

  • Real Claude Code processes plus SQLite memory so work survives across sessions.
  • Cron with priority/quota awareness; Telegram/WhatsApp/iMessage outside the terminal.
  • Per-session skills/MCP with safety gates; MIT open source.
Read full story
Linked Models & Agents:

Hermes Agent v0.21.0: cron doctor, in-menu /plan, nested todos, stepwise code sessions

Nous Hermes Agent v0.21.0 ships hermes cron doctor for failed/silent scheduled jobs, puts /plan in the menu with Telegram command search, adds nested todo subtasks, keeps files loaded across stepwise code runs with long outputs saved for reread, and hot-updates settings on long-lived sessions without restart.

Key Takeaways

  • Ops: hermes cron doctor lists failed, undelivered, and silently stopped cron jobs.
  • Planning: /plan in menu; Telegram word-search across commands and skills.
  • Runtime: nested todos + files kept across stepwise runs; long-lived sessions hot-update settings.
Read full story
Linked Models & Agents: