Founders & builders from @WorkOS, @nginx, @PingCAP, @mozilla, @strapijs, @zitadel, @StirlingPDF, Caution, @EntireHQ, Guepard, Confident AI, @papercompute, @modaicdev and more are coming 👀

localhost(san-francisco) is next week 🔥 Oct 14: the people who maintain, break and ship open source, in one room. No panel, no pitch. Hosted by @sentry, co-organized with @superset_sh, @PlakarKorp, @OpenSpec_ & @commitvc. Word of mouth almost filled the room → luma.com/hddco7hd

💡 ships its own compression model, Kompress-v2-base, on Hugging Face. That's a wrap on OSSCAR Q2 Scaling 🎬 Full ranking → osscar.dev

🏆 #1 OSSCAR Scaling · Q2 2026: Headroom Labs Its main repo, Headroom, shrinks tool output, logs & RAG chunks before they hit the model — fewer tokens, same answer. 📅 Jan 2026 · 📈 org: ~57K stars (47x+) · 152 contribs (9x+) · ~1.5M dls (64x+)

💡 already used by tldraw & TanStack. That's a wrap on OSSCAR Q2 Emerging 🎬 Full ranking → osscar.dev

🏆 #1 OSSCAR Emerging · Q2 2026: HeyGen @HeyGen Their main repo, HyperFrames, turns plain HTML into video rendered for AI agents. 📅 Mar 2026 · 📈 org this Q: ~34K stars (300x+) · 46 contribs (7x+) · ~3M dls (150x+)

💡 Launched days after Anthropic's closed-source Claude Design — the open, self-hostable, bring-your-own-model answer. #1 tomorrow → osscar.dev

🥈 #2 OSSCAR Scaling · Q2 2026: nexu Its main repo, open-design, is the open-source, local-first Claude Design alternative — any coding agent becomes the design engine, on any model via BYOK. 📅 Apr 2026 · 📈 org this Q: ~91K stars (36x+) · 394 contribs (24x+)

💡 Ships "Polly" (a multi-agent orchestrator that writes no code) & "Debby" (a Claude+GPT brainstorm partner). #1 tomorrow → osscar.dev

🥈 #2 OSSCAR Emerging · Q2 2026: omnigent An open-source meta-harness giving Claude Code, Codex & Pi a common Python layer: policies, OS-level sandboxing, shareable live sessions. 📅 Jun 2026 · 📈 org this Q: ~6K stars (14x+) · 102 contribs (100x+) · ~53K dls (38x+)

💡 Documents 71.5× fewer tokens per query vs reading raw files, tagging every edge EXTRACTED / INFERRED / AMBIGUOUS. #2 tomorrow → osscar.dev

🥉 #3 OSSCAR Scaling · Q2 2026: Graphify Labs @graphify Their main repo: an on-device CLI that maps your codebase into a knowledge graph agents traverse instead of grepping. 📅 Apr 2026 · 📈 org this Q: ~79K stars (3x+) · 117 contribs (19x+) · ~2.4M dls (30x+)

💡 Reports top scores on the LongMemEval & BEAM long-term-memory benchmarks. #2 tomorrow → osscar.dev

🥉 #3 OSSCAR Emerging · Q2 2026: Mnemosyne OSS @mnemosyne_oss A zero-dependency, SQLite-backed memory system giving agents long-term context in one file. 📅 Apr 2026 · 📈 org this Q: ~1.4K stars (∞) · 49 contribs (49x+) · ~40K dls (95x+)

4️⃣ Cursor (@cursor_ai) — the AI-native code editor rebuilt around agents writing most of the code The podium starts tomorrow: #3, then #2, then #1 🏆 Follow @supabase and @commitvc for the finale

6️⃣ jo (@askjoai) — a personal AI agent on your Mac that preps your day from mail and calendar overnight 5️⃣ CloakHQ — CloakBrowser, a stealth Chromium fork that slips past bot-detection in Playwright

8️⃣ walkinglabs — an open-source lab producing tools and research for agentic AI and reinforcement learning 7️⃣ Orca ADE (@orca_build) — an open-source IDE for agents, running Claude Code, Codex & Cursor CLI in parallel

1️⃣0️⃣ multica-ai (@MulticaAI) — a managed-agents platform that treats coding agents as teammates you assign issues to 9️⃣ getpaseo — an environment orchestrating multiple coding agents from desktop, mobile and CLI

OSSCAR Q2 2026 · Scaling 📈 The Top 10 is here — ranks #10 → #4 👇 Ranked by @supabase and @commitvc · osscar.dev

4️⃣ Refactoring (@tolariamd) — Tolaria, a local-first, git-backed desktop app for managing markdown knowledge bases as AI-ready context The podium starts tomorrow: #3, then #2, then #1 🏆 Follow @supabase and @commitvc for the finale