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.
Agno v2.2.11 adds ParallelTools for web search/extraction, Claude context editing, Anthropic beta access, and expanded Gmail label management.
└──▷ GET THIS VERSION
$ git clone --branch v2.2.11 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:$ git checkout v2.2.11
└──▷ USE IT
Run AI-optimized parallel web search and content extraction inside an agent using the new ParallelTools toolkit.
python
from agno.tools.parallel_tools import ParallelTools
agent = Agent(
tools=[ParallelTools()],
...
)
agent.run('Find and summarize the latest research on LLM context management')
›Adds ParallelTools toolkit providing AI-optimized web search and content extraction via both direct API integration and MCP server support.
›Enables all Anthropic API beta features on Agno Claude models via the betas parameter.
›Adds duration field to top-level Workflow metrics, exposing total runtime of a complete Workflow run.
›Extends the Gmail tool with label management: list custom labels, apply labels to emails, remove labels from emails, and delete custom labels.
Crush v0.17.0 adds a recent-models picker and opt-in AI attribution trailers to git commits.
└──▷ GET THIS VERSION
$ git clone --branch v0.17.0 https://github.com/charmbracelet/crush.git
# already have the repo? check out this version:$ git checkout v0.17.0
›Adds a 'recent models' section at the top of the model picker so frequently used models are surfaced automatically.
›Adds trailer_style config option to append an Assisted-by git trailer (e.g. Assisted-by: Claude Sonnet 4.5 via Crush) to commits, following Fedora Council AI-disclosure guidelines.
›Migrates the deprecated co_authored_by config setting to the new attribution scheme.
Qwen Code v0.2.0-preview.0 adds TodoWriteTool and TaskTool support to the Zed editor integration.
└──▷ GET THIS VERSION
$ git clone --branch v0.2.0-preview.0 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.2.0-preview.0
›Adds TodoWriteTool and TaskTool support to the Zed editor integration, enabling task and to-do management workflows within Zed.
Qwen Code v0.2.1-nightly adds TodoWriteTool and TaskTool support to its Zed editor integration.
└──▷ GET THIS VERSION
$ git clone --branch v0.2.1-nightly.20251112.22edef0c https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.2.1-nightly.20251112.22edef0c
›Adds TodoWriteTool and TaskTool support to the Zed editor integration, enabling task and to-do management workflows from within Zed.
$ git clone --branch v0.16.0-nightly.20251112.c961f274 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.16.0-nightly.20251112.c961f274
›Adds CLI flags for session management, including the ability to resume previous geminiChat sessions.
›Adds a setting to disable GitHub extensions from the CLI.
›Enhances the RipGrep tool with advanced search options and improved defaults.
›Enhances loop detection with a 2-stage check for more reliable agentic runs.
›Adds expected_replacements parameter to the smart-edit tool for more precise edits.
+2 moreshow less
›Adds experiment logging and a caching experiment for performance optimization.
›Supports Ink scrolling for improved terminal rendering of long outputs.
gemini-cli v0.15.0 adds session resumption flags, a hook execution engine, /extensions restart, and an a2a listCommands endpoint.
└──▷ GET THIS VERSION
$ git clone --branch v0.15.0-preview.0 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.15.0-preview.0
└──▷ TRY IT
Restart all loaded extensions after editing their configuration, without restarting the CLI.
$ /extensions restart
›Adds CLI flags for session management and resuming chat sessions via geminiChat.
›Introduces a Hook Execution Engine for automating actions around tool calls and model responses.
›Adds /extensions restart slash command to reload extensions without restarting the CLI.
›Gemini memory now reloads automatically on extension load/unload.
›Extension reloading now respects updates to excluded tools.
+6 moreshow less
›Adds listCommands endpoint to the a2a server for agent-to-agent capability discovery.
›Adds setting to disable GitHub extensions.
›Adds expected_replacements parameter to the smart-edit tool for more precise edits.
›Switches to alternate buffer mode before rendering Ink for a cleaner terminal UI.
›Supports scrolling in the Ink UI.
›Tabs are now preserved on paste.
└──▷ BREAKING ON UPGRADE
!The icon property on info messages is renamed to prefix.
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Ollama v0.12.11 adds log probability support to its API and opt-in Vulkan GPU acceleration.
└──▷ GET THIS VERSION
$ git clone --branch v0.12.11 https://github.com/ollama/ollama.git
# already have the repo? check out this version:$ git checkout v0.12.11
└──▷ TRY IT
Retrieve per-token log probabilities to evaluate model confidence on a generation — useful for perplexity scoring or classification pipelines.
$ curl http://localhost:11434/api/generate -d '{"model": "gemma3", "prompt": "Why is the sky blue?", "logprobs": true}'
Inspect the top 3 alternative tokens at each position to understand model uncertainty or build autocomplete candidates.
$ curl http://localhost:11434/api/generate -d '{"model": "gemma3", "prompt": "Why is the sky blue?", "logprobs": true, "top_logprobs": 3}'
Enable Vulkan acceleration to run models on AMD, Intel, or integrated GPUs not supported by the default CUDA/Metal backends.
$ OLLAMA_VULKAN=1 ollama serve
›Adds logprobs field to Ollama's generate API and OpenAI-compatible API, returning per-token log probabilities and raw bytes for classification, evaluation, and perplexity tasks.
›Adds top_logprobs parameter to expose the N most-likely alternative tokens at each position, enabling token-level introspection.
›Adds opt-in Vulkan GPU acceleration via OLLAMA_VULKAN=1, broadening hardware support to AMD, Intel, and integrated GPUs.
›Adds WebP image support in Ollama's desktop app.
›Ollama now prefers dedicated GPUs over iGPUs when scheduling models.
Phoenix Evals 2.6.0 adds Anthropic and Google GenAI adapters, GPT-5 on Azure, and invocation params for ClassificationEvaluators.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-evals-v2.6.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-evals-v2.6.0
›Adds support for invocation params in ClassificationEvaluators, enabling per-evaluation model parameter control.
›Adds Anthropic and Google GenAI adapters for use with Phoenix evals.
›Adds GPT-5 support to Azure OpenAI model integrations.
Arize Phoenix client v1.23.0 adds retry support for experiments.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-client-v1.23.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-client-v1.23.0
›Adds retry support for experiments, allowing failed experiment runs to be automatically retried.
THE AI TOOLCHAIN