vibehacker
News
GitHub / EverMind Raven ·

EverMind open-sources Raven, a host agent that orchestrates Claude Code, Codex, and its own specialists

Raven (Apache-2.0, pre-alpha) has a Host Agent split a goal into a dependency graph and hand each piece to its built-in research, code, design, and on-call agents or to 13 preset third-party agents like Claude Code, Codex, and OpenCode, while a separate Evolver keeps only harness changes that pass benchmark checks. Install with curl -fsSL https://raven.evermind.ai/install.sh | bash, or run it in Docker and open localhost:18793.

Read at github.com
Claude Code
An AI coding agent for terminal, IDE, web, and Slack

More news

View all

pulpie-mcp lets coding agents crawl whole doc sites into clean local Markdown

The new Apache 2.0 MCP server gives Claude Code, Codex, and other clients four tools to fetch, save, and crawl docs as full Markdown (tables and code intact, not summarized), using a local 210M parameter extraction model in about 420 MB of VRAM; the author crawled 60 pages in about 49 seconds. Install with uv tool install git+https://github.com/pinkpixel dev/pulpie mcp , but note the bundled model is CC BY NC 4.0, so non commercial use only by default…

GitHub / pulpie-mcp (DEV post)

Show HN: Pi pod runs pi coding-agent sessions in isolated sandboxes on your own server

The open source pi pod puts each pi agent session in its own container on a VM you host, with agent config defined at the org, user, and project level so a team can share it, and a locally rendered TUI so typing doesn't lag over SSH. Native mobile apps are built from source for now, a hosted version is coming, and HN commenters note containers alone aren't a hard security boundary…

Show HN / pi pod

Microsoft's Agensh: leaderless coding-agent teams keep improving from 1 to 1,024 agents

Agensh drops the central orchestrator: each worker claims its own sub task, builds and tests it, and merges into a shared Git repo while posting findings to a shared board, all on top of a Copilot single agent harness with a 6 hour budget. On ProgramBench's five hardest tasks with GPT 5.6 sol, going from 1 to 128 agents lifted the mean test pass rate from 19.31% to 28.78%, and 1,024 agents pushed pandoc from 33.89% to 55.06%, though the paper doesn't report what large teams cost…

arXiv / Microsoft Research

Strata runs the 125B Qwen3.8-Flash-Next on a 12 GB gaming GPU, fully local

MIT licensed Strata is a one click Windows/Linux installer that serves Qwen3.8 Flash Next behind OpenAI and Anthropic compatible APIs on localhost, so you can point Claude Code, Cursor, or Codex at it; the author measured 53–94 tokens/s on an RTX 5070 (12 GB) with 64 GB RAM. You need 32 GB+ RAM and about 80 GB of disk, and the PC can freeze for 1–3 minutes while the model loads…

GitHub / Strata (HN front page)

Spotted something we missed? Start a thread.