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.
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…
Give pve agents a repo, a ref, and a task, and it clones a clean LXC template on your Proxmox host, starts a Claude Code agent inside, and streams the full transcript to your browser, where you also answer permission prompts. Workspaces run in parallel and stay off your workstation; review per file diffs, then push to the workspace's own branch or throw it all away…
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…
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…
Ju Lin's MIT licensed Rio runs a task to completion with no chat or mid run steering, acting by patching Python, shell, and %%edit cells in a live Jupyter kernel instead of growing a conversation history. Install with uv tool install rio , log in to Anthropic, Codex, or GitHub Copilot, then rio run "Fix gh issue 123." or point it at a task.md…
Spotted something we missed? Start a thread.