Tag
15 posts tagged Open Source.
The v0.3.4 + v0.3.5 wave: voice orchestration with live floor context and full app control, markdown previews everywhere, commit history and branch compare in the built-in IDE, a six-tab Settings redesign, xAI Grok and Kimi Code engines, auto-update, and a queue that always has an escape hatch.
An honest comparison of YC's qm and Munder Difflin: both orchestrate fleets of CLI coding agents with security postures, scheduled background work, and Slack — one as a headless multiplayer harness for teams, one as a local-first desktop office with real terminals, voice, and a built-in IDE.
Munder Difflin v0.3.3 adds a full Monaco IDE — file tree, editor tabs, save, and side-by-side git diffs of your agents' changes — plus GitHub Copilot CLI as a first-class agent engine, our first community-contributed provider.
Munder Difflin v0.3.2 adds Realtime Michael — a low-latency voice channel to the GOD orchestrator. Talk to Michael and he listens, answers, and acts: reading the hive and, behind spoken echo-back confirmation, dispatching, spawning, and steering the floor in real time.
Munder Difflin v0.3.1 runs your agent floor on open-weight models — gpt-oss, Qwen3, DeepSeek, Llama, Mistral, GLM, Kimi — either fully local (Ollama/LM Studio/vLLM) or through a third-party OSS provider. Here's how to wire each across the OpenCode, Crush, and pi engines.
Munder Difflin v0.3.0 makes every hire — and Michael himself — a pluggable engine, adds an integrations registry with a write-only secret broker, and lets the god orchestrator spawn an ephemeral worker straight from Slack.
Munder Difflin v0.2.8 ships Shareable Hires: a one-click, portable agent role manifest + The Hiring Fair gallery. Click a hire link, review every field, then spawn it yourself.
Why agent roles should be portable: what a hire manifest encodes, how one-click hiring stays safe, and how The Hiring Fair turns tacit setup into a shareable artifact.
How Munder Difflin's blog is written by an automated writer agent in the hive — drafts in a worktree, single-committer integration, Eleventy build, human-gated deploy. Build your own.
A how-to for standing up a fully automated PR-reviewing agent in Munder Difflin — one that reads your real source (not just the PR description), de-dupes noise, and only escalates what matters. With a real triage run that turned 22 duplicate firings into a clean v0.2.5 patch queue.
Munder Difflin v0.2.4 is here: Claude Code, OpenAI Codex, and Antigravity (Gemini) agents now run as one hive with full parity — no API keys, no setup. Brief a GOD orchestrator, automate basically anything in one prompt, and close the lid while it keeps working.
Munder Difflin v0.2.0 is here: a Command Center overhaul, per-agent token budgets, live OpenTelemetry observability, a circuit breaker, durable SQLite persistence, and a big round of community fixes.
How a single prompt to the Munder Difflin god agent reviewed all open PRs and set up a recurring hourly PR reviewer — while the repo was blowing up with 400+ stars.
Agents touch your code, keys, and memory. That's why agent tooling should be open source and local-first — so you can verify it, not just trust it.
The origin story of Munder Difflin — how the pain of juggling Claude Code terminals led to a coordinated, memory-backed hive of agents you can watch.