Backfill issue -081 — The AI Toolchain

EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW

ISSUE VIEW full issue

Do you prefer this view?

$ tct list   # 5 tools matched

AI & LLM Tooling

◆ Local LLM Runtimes

KoboldCpp

v1.114.1 NOTES

KoboldCpp v1.114.1 adds parallel text generation, distributed RPC GPU sharing, LTX2.3 video gen, and new image models.

└──▷ GET THIS VERSION

$ git clone --branch v1.114.1 https://github.com/LostRuins/koboldcpp.git
# already have the repo? check out this version:
$ git checkout v1.114.1

└──▷ TRY IT

Host a KoboldCpp instance that handles up to 4 simultaneous text generation requests — useful for multi-user or Horde deployments.

$ koboldcpp --model model.gguf --parallelrequests 4

Share your local GPU over the network for distributed inference across multiple machines.

$ koboldcpp --rpcmode host --rpcport 5551

Connect to a remote shared GPU for distributed inference, specifying the RPC host target.

$ koboldcpp --model model.gguf --rpcmode connect --rpctargets 192.168.1.50:5551

›Adds --parallelrequests X flag to enable experimental continuous batching, allowing X simultaneous text generation requests instead of queuing — useful for multi-user hosting or Horde deployments.
›Adds --rpcmode (connect or host) and --rpctargets flags plus --rpcport (default 5551) for RPC backend support, enabling distributed inference across multiple GPUs over the network.
›Adds --jinjathink [default/true/false] flag (and GUI dropdown) to toggle model thinking mode, which internally sets the thinking_enabled jinja kwarg.
›Adds chat_template_kwargs field to the API for passing jinja kwargs objects directly via API calls.
›Adds --sdtiledvae 1 flag (hotfix) to enable VAE tiling for video generation.

+9 moreshow less

›Adds --noswa flag to disable Sliding Window Attention, which is now on by default for all models that support it.
›Adds support for LTX2.3 video generation (txt2vid and img2vid) via the SDUI at http://localhost:5001/sdui, including AVI download with audio.
›Adds support for Microsoft Lens, HiDream o1, LongCat, and Ernie image generation models.
›Adds support for setting individual devices for CLIP and VAE in image generation.
›Adds support for loading custom TAE (Tiny Auto Encoder) image VAEs via the VAE file selector.
›Adds multithreaded MP3 generation for AceStep with a new default bitrate of 192kbps.
›Adds FPS controls, increased max frame limit, and option to continue video generation from the final frame.
›Adds Sampler and Scheduler settings for ComfyUI remote endpoints and A1111-compatible endpoints in Kobold Lite.
›Adds BotBooru support to the Import Character from Website URL feature in Kobold Lite.

└──▷ BREAKING ON UPGRADE

!The GPU ID list in the GUI launcher is now 0-based index (0,1,2,3) instead of 1-based (1,2,3,4); existing GUI configurations referencing GPU IDs by 1-based index will target the wrong device.
!SWA (Sliding Window Attention) is now enabled by default on all models that support it (was off by default); use --noswa or uncheck the SWA checkbox in the GUI launcher to restore previous behavior.

Was this useful?

LocalAI

v4.3.6 NOTES

LocalAI v4.3.6 adds NVIDIA NeMo Parakeet ASR backend and hardens outbound HTTP redirect handling.

└──▷ GET THIS VERSION

$ git clone --branch v4.3.6 https://github.com/mudler/LocalAI.git
# already have the repo? check out this version:
$ git checkout v4.3.6

›Adds NVIDIA NeMo Parakeet ASR backend (parakeet-cpp) for automatic speech recognition via the parakeet.cpp integration.
›Hardens outbound HTTP clients to refuse redirects, reducing server-side request forgery exposure via pkg/httpclient.

Was this useful?

llama.cpp

b9437 2 RELEASES · 2026-05-30 NOTES STABLE

llama-bench gains -fa auto support and -ngl now defaults to -1.

└──▷ GET THIS VERSION

$ git clone --branch b9437 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9437

›Adds -fa auto option to llama-bench, enabling automatic flash-attention mode selection during benchmarking.
›Changes the default value of -ngl in llama-bench to -1, aligning it with the behavior of other llama.cpp tools.

1 more release in this issue · 2026-05-30

b9436 NOTES STABLE

llama.cpp b9436 adds bf16 support for OpenCL backend via f16 conversion

└──▷ GET THIS VERSION

$ git clone --branch b9436 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9436

›Adds bf16 support to the OpenCL backend by converting to f16 at runtime, enabling bf16 model inference on OpenCL-capable GPUs.

Was this useful?

◆ AI Agent Frameworks

OpenClaw

v2026.5.28 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.5.28 adds Claude Opus 4.8, encrypted PDF extraction, GitHub Copilot agent runtime, policy conformance checks, and Workboard agent coordination tools.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.28 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.28

└──▷ TRY IT

Check the status of all running agents, including active subagent details introduced in this release.

$ openclaw status

›Adds Claude Opus 4.8 as a supported provider model.
›Adds GitHub Copilot agent runtime and Codex Supervisor plugin package for delegated Codex workflows.
›Supports encrypted PDF extraction via ClawPDF integration.
›Surfaces MCP structured content in agent tool results.
›Adds Fal Krea image model schemas and NVIDIA featured model catalogs.

+11 moreshow less

›Adds MiniMax streaming music response support.
›Adds provider-backed voice model catalogs.
›Adds Workboard agent coordination tools for tracking and handing off active agent work.
›Adds policy comparison, ingress-channel conformance, and sandbox-posture conformance checks.
›Shows active subagent details in status output.
›Adds Plugin SDK reply payload sending hook for plugins that deliver channel-owned replies.
›Adds ClawHub plugin display names plus skill verification and trust surfaces.
›Externalizes GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata.
›Shows commentary in progress drafts for live Discord runs.
›Adds iOS Pro app refresh including Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback.
›Expands default Diffs language coverage with a split language pack.

Was this useful?

◆ AI Coding Agents

SST OpenCode

v1.15.13 NOTES

The open source coding agent.

OpenCode v1.15.13 adds session metadata storage via API/SDK and smarter config loading from the opened directory upward.

└──▷ GET THIS VERSION

$ git clone --branch v1.15.13 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.15.13

›Enables storing custom metadata on sessions through the API and SDK.
›Config now loads from the opened location upward, applying directory-specific settings and provider policies more predictably.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · May 30, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -081, May 30, 2026

KoboldCpp

LocalAI

llama.cpp

OpenClaw

SST OpenCode