Keel drops local-first macOS coding workspace

// 20h agoOPENSOURCE RELEASE

Keel drops local-first macOS coding workspace

Keel is an open-source, local-first macOS coding workspace written in Rust and GPUI that introduces a host-verified decision architecture for AI agents. Instead of giving models full execution control, Keel prepares and verifies candidate routes before execution, supporting both local Core ML inference and hosted selectors via the Agent Client Protocol.

// ANALYSIS

Constraining AI agents to host-vetted candidate options rather than open-ended tool loops represents the realistic path forward for reliable agentic software development.

–Host-enforced permission model: The selector chooses among pre-filtered options, but Keel's host application retains exclusive authority over task execution and validation.
–Flexible local-first architecture: Incorporates on-device Apple Silicon inference via Core ML (Laya) alongside optional hosted decision providers (Jev).
–Modular agent interoperability: Integrates with external coding agents through the Agent Client Protocol (ACP) while maintaining separate harness fallbacks if selectors abstain.
–Explicit abstention over hallucination: Built-in abstention thresholds gracefully route uncertain tasks back to standard manual or harness paths without breaking developer workflows.

// TAGS

keeljevrustgpuiagentagentic-codingcore-mlmacoslocal-aiopensource

DISCOVERED

20h ago

2026-09-23

PUBLISHED

21h ago

2026-09-23

RELEVANCE

6/ 10

AUTHOR

Av1dlive

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE59m ago

PrismaX opens robotics teleoperation datasets to AI teams

PrismaX has opened access to its real-world robotics teleoperation dataset for AI training teams developing physical AI and foundation models. Backed by a16z crypto, the San Francisco-based startup coordinates human teleoperators, robot hardware owners, and AI researchers to record, validate, and aggregate demonstration trajectories across complex manipulation tasks.

LAUNCH1h ago

Siren demos autonomous marketing agent with MCP

Siren is an autonomous marketing platform that generates code-rendered launch videos, ad creatives, and social copy from a single prompt and automatically distributes them across social channels. Operating via a web dashboard and an MCP server, it allows developers to orchestrate marketing asset creation and publishing directly inside coding environments like Cursor and Claude Code.

OPEN SOURCE1h ago

stable-diffusion.cpp brings dependency-free diffusion inference to C++

stable-diffusion.cpp is an open-source implementation enabling lightweight and efficient inference of major generative diffusion architectures, including Stable Diffusion, Flux, Wan, and Qwen Image, using pure C and C++. Modeled after the ggml ecosystem, the project removes heavyweight Python dependencies and framework overhead, enabling cross-platform local generation across standard consumer CPUs and accelerators with minimal resource footprints.

Keel drops local-first macOS coding workspace