The AI Toolchain — issue -053, June 27, 2026

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Cline CLI v3.0.31 adds marketplace uninstall support, quoted prompts for one-shot mode, and ClinePass subscription prompts.

$ git clone --branch cli-v3.0.31 https://github.com/cline/cline.git
# already have the repo? check out this version:
$ git checkout cli-v3.0.31

• ›Adds marketplace uninstall support and surfaces plugin-bundled skills in the marketplace.
• ›Requires quoted prompts for one-shot mode, enforcing cleaner CLI invocation.
• ›Prompts users to switch to ClinePass when credits run out, listing ClinePass features in the unsubscribed state.
• ›Adds an option to open the subscription page directly from ClinePass options.
• ›Shows when a request cost is covered by a Cline subscription.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

CrewAI 1.15.1 adds automatic Git init for new projects, enforces explicit crew definitions, and opens the deployment page post-deploy.

$ git clone --branch 1.15.1 https://github.com/crewAIInc/crewAI.git
# already have the repo? check out this version:
$ git checkout 1.15.1

• ›Automatically initializes a Git repository when generating a new CrewAI project.
• ›Requires explicit CrewAI project definitions, enforcing structured crew configuration at project creation.
• ›Opens the deployment page in the browser automatically after running a CLI deploy.

KoboldCpp v1.116.1 adds Krea 2 Turbo, Ideogram 4, Boogu Edit image models, MCP server support, and new CLI flags.

$ git clone --branch v1.116.1 https://github.com/LostRuins/koboldcpp.git
# already have the repo? check out this version:
$ git checkout v1.116.1

$ koboldcpp --config mymodel.kcpps --allow-config-onready

$ curl http://localhost:5001/v1/audio/speech -H 'Content-Type: application/json' -d '{"model": "tts", "input": "Hello world", "response_format": "mp3"}' --output speech.mp3

$ koboldcpp-mac-arm64 --config mymodel.kcpps --failsafe

• ›Adds --allow-config-onready CLI flag, which re-enables --onready commands from config files when swapping .kcpps configs via API or Web UI; must be triggered directly from the terminal and cannot be saved.
• ›Adds --failsafe CLI flag for macOS builds to use Accelerate only, bypassing Metal.
• ›Adds response_format: mp3 support to the TTS API endpoint for saving TTS outputs as MP3, following the OpenAI API spec.
• ›Adds MCP server support to the built-in llama.cpp Web UI.
• ›Adds Krea 2 Turbo image generation model support (recommended: 8 steps at 1.0 guidance CFG); template available as Krea2Turbo.kcppt.

OpenCL Flash Attention gains f16/f32/q4_0/q8_0 support with prefill prepass kernels and tile-skip optimizations.

$ git clone --branch b9828 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9828

• ›Adds OpenCL Flash Attention prefill prepass kernels (flash_attn_kv_pad_f16, flash_attn_mask_pad_f16, flash_attn_blk_f16) that classify KV tiles as fully masked, mixed, or fully unmasked — enabling the main kernel to skip fully-masked tiles and bypass mask lookups for fully-unmasked ones.
• ›Adds OpenCL FA kernels for q4_0 and q8_0 quantization formats, extending Flash Attention beyond f16/f32 on Adreno and compatible OpenCL backends.
• ›Adds OpenCL set_rows operation supporting f32-to-q8_0/q4_0 conversion.
• ›Adds OpenCL dequantization kernels for q4_0 and q8_0.
• ›Adds an OpenCL FA tile tuning table with a per-device override mechanism.