Microsoft Open Source Blog · Oct 20, 2026 · 9:23 AM

Microsoft open-sources Scope, a self-hosted platform for testing how coding agents use your SDK, docs, or MCP server

Scope (MIT) runs the same task through agents like GitHub Copilot and Claude Code over repeated runs, scores each against a dependency graph of criteria with an LLM judge, and keeps tool calls, logs, and workspace snapshots so you can trace where an agent got stuck. There's no hosted version: you run it locally with Docker Compose or on Kubernetes via Helm, and the default worker needs a Copilot entitlement (GitHub).

Read at opensource.microsoft.com

More news

View all

Lights-on software factory boilerplate moves Claude Code orchestration into deterministic scripts

The MIT repo, built from the setup behind Votito, bundles a sandboxed Claude Code container, a bash command regulator that auto approves or denies with guidance, a lint on edit PostToolUse hook, and a generator that turns a plan into multi agent workflow scripts with test gates. Its author says moving that orchestration out of the LLM cut token spend by about 80% versus a bare Claude workflow (Show HN)…

GitHub (gojko/lights-on-software-factory) 2 hours ago

Tess-4.5-27B open-weights coding model matches its Qwen base using 25% fewer tokens

Fine tuned from Qwen3.8 27B on 127 real engineering sessions, it ties its base at 133/150 on BenchLocal while generating 25% fewer tokens, and its multi token prediction draft head roughly doubles code generation on an RTX 4090 (49 to 96 tokens/sec). Apache 2.0 BF16 and GGUF weights are on Hugging Face, and the benchmarks are Continuity Research's own runs…

Continuity Research 3 hours ago

Claude Code 2.1.304 adds /auto-mode-setup, which reads your project to teach auto mode your environment

The guided setup learns from your project and recent sessions and now also runs on Bedrock, Vertex, Foundry, and telemetry disabled sessions, while the new /claude api managed agents secure checks a Managed Agents config against Anthropic's security guide without changing anything. Pro and Max users also get a warning before resuming an idle conversation would eat a noticeable share of their 5 hour usage limit…

GitHub (anthropics/claude-code) 4 hours ago

Spinoza Labs' Vortex Code compiles a blueprint first, then has a swarm of agents build against it

The new coding CLI has Agent, Build (parallel tasks gated by tests), and Architect modes; Architect turns an approved blueprint into a plan its Agent OS compiler hands to parallel agents, and Spinoza's demo is a 173,773 line finance terminal built from 1,111 commits. Pro Architect costs $200/month, which per the founder on HN includes $200 in token usage…

Spinoza Labs 5 hours ago

Fade lets you keep talking to one agent in your terminal while a second Builder agent writes the code

Built on the Pi harness, Fade runs a conversational companion and a Builder side by side so you can plan or line up tasks mid build, and it only marks work "checked" after committing the change and re running the Builder's own test or command proofs itself. It's an early, self described rough v0.5 (MIT, Node 22.19+, works with any Pi provider including Ollama), commits straight to your current branch, and has a no key npx @muzaffermahi/fade demo to try first…

GitHub (muzaffermahi/Fade) 6 hours ago

Spotted something we missed? Start a thread.