morluto/rea (146,406★, +45,495 today) holds the #1 spot on GitHub trending for a second straight day, with an even bigger one-day gain than yesterday. mksglu/context-mode (27,096★) sandboxes MCP tool output to cut context usage by 98% via MCP + hooks. cathrynlavery/diagram-design (52,255★) lets agents draw custom-branded diagrams instead of Mermaid. microsoft/BitNet (40,826★) keeps optimizing 1-bit model inference on CPU/GPU. Agno v3.1.3 lets ClaudeAgent/CodexAgent sessions resume on any replica, run in the background, and replay step by step.
appwrite/appwrite (57,624★) pivots from a developer backend-as-a-service to a cloud that exposes an MCP interface agents can call directly. DeusData/codebase-memory-mcp (46,293★) replaces embedding-based RAG with an AST-plus-knowledge-graph MCP server that indexes an entire codebase into a single queryable binary. Yeachan-Heo/oh-my-claudecode (39,768★) bolts the multi-agent team orchestration layer Claude Code doesn't ship natively. sgl-project/sglang (36,965★) is trending because agentic workloads — not single-turn chat — are now what inference frameworks optimize for first. Agno v3.1.2 adds Conversation Compaction to fold old turns into a summary, plus a new Codex External Agent adapter.
JustVugg/colibri uses memory tiering across storage/RAM/VRAM to run 744B–2.8T MoE models on consumer hardware in pure C; tech-leads-club/agent-skills wants to get supply-chain verification for agent skills sorted out before they become the next npm trust problem; alphaXiv/OpenResearch turns Claude Code / Codex into experiment-running researchers with git-native reproducibility; calesthio/OpenMontage wraps 12 production pipelines, 100+ tools, and 700+ agent skill files into a full video production framework; alibaba/open-code-review open-sources their hybrid 'rule engine + LLM agent' code review tool; Claude Code v2.1.269 raises the Workflow tool's concurrent agent cap to 256
Baseten puts custom-model packaging, GPU deployment, inference engines, autoscaling, and release workflows on one platform. Its value is not another OpenAI API, but retaining runtime control while operating less GPU orchestration.