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.
Continue's OpenAI adapters 1.9.0 adds GPT-OSS support on Bedrock and hardens file-read security.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds gpt-oss model support to the Amazon Bedrock provider.
›Introduces a secure image component to guard against unsafe image rendering.
Continue v1.0.80 adds GPT-OSS on Bedrock, Kimi K2 native tools, and unsafe file read prevention.
└──▷ GET THIS VERSION
$ git clone --branch v1.0.80-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout v1.0.80-vscode
›Adds gpt-oss model support to the AWS Bedrock provider.
›Enables native tool support for Kimi K2 models.
›Adds protection against unsafe file reads to harden the extension against malicious workspace content.
›Updates the default-included context providers.
›Wraps each recently viewed code snippet inside a token block for clearer context attribution.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Goose v1.6.0 adds mTLS for all providers, PKCE auth, message queue with interruption handling, and in-place message editing.
└──▷ GET THIS VERSION
$ git clone --branch v1.6.0 https://github.com/block/goose.git
# already have the repo? check out this version:$ git checkout v1.6.0
└──▷ TRY IT
Allow Goose to automatically load project-level agent instructions without any extra flags.
$ # Place an AGENTS.md file in your project root; Goose reads it by default on startup
echo '# Agent Instructions
Always use TypeScript.' > AGENTS.md
goose session
›Adds mTLS support across all providers for mutual-authentication to AI backends.
›Adds PKCE support for the Tetrate Agent Router Service authentication flow.
›New message queue system with interruption handling for more reliable agent interactions.
›Providers can now configure a fast model specifically for summarization tasks.
Qwen Code v0.0.8-nightly.7 adds .geminiignore support in grep, grep result limits, deterministic cache control, and save location options.
└──▷ GET THIS VERSION
$ git clone --branch v0.0.8-nightly.7 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.0.8-nightly.7
›Grep tool now respects .geminiignore to exclude files and directories from search results, consistent with other tool behaviors.
›Adds a project/global save location option, letting users control where session data is persisted.
›Adds deterministic cache control for LLM requests.
An open-source AI agent that brings the power of Gemini directly into your terminal.
gemini-cli v0.3.0-nightly adds prompt completion, screen reader mode, IDE stdio MCP connections, and editable string settings.
└──▷ GET THIS VERSION
$ git clone --branch v0.3.0-nightly.20250822.15c62bad https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.3.0-nightly.20250822.15c62bad
›Adds prompt completion in the CLI for faster, tab-assisted input.
›Introduces a screen reader mode flag for accessibility support.
›Supports IDE connections via stdio MCP, enabling editor integrations.
›Enables editing of string settings directly from the settings UI.
langchain-ollama 0.3.7 adds string-value support for reasoning intensity levels (e.g. gpt-oss).
└──▷ GET THIS VERSION
$ git clone --branch langchain-ollama==0.3.7 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-ollama==0.3.7
›Extends the reasoning type to accept string values for custom intensity levels such as gpt-oss, enabling fine-grained reasoning control beyond preset options.
LlamaIndex v0.13.3 adds Heroku embeddings, Qdrant sharding, instruction-enhanced Ollama embeddings, and GPT-5 model support.
└──▷ GET THIS VERSION
$ git clone --branch v0.13.3 https://github.com/run-llama/llama_index.git
# already have the repo? check out this version:$ git checkout v0.13.3
└──▷ USE IT
Point an existing OpenAI LLM config at GPT-5 to start testing the new model.
python
from llama_index.llms.openai import OpenAI
llm = OpenAI(model="gpt-5-chat-latest")
response = llm.complete("Summarize the MITRE ATT&CK framework in three sentences.")
print(response)
›Adds HerokuEmbeddings class in new llama-index-embeddings-heroku 0.1.0 package for embedding via Heroku-hosted models.
›Adds instruction support to OllamaEmbedding in llama-index-embeddings-ollama, enabling instruction-prefixed embedding requests.
›Adds gpt-5-chat-latest model support to llama-index-llms-openai.
›Adds Qdrant sharding support to llama-index-vector-stores-qdrant.
OpenAI Agents SDK v0.2.9 adds lifecycle hooks, SQLAlchemy history backend, MCP retry logic, and realtime input timeouts.
└──▷ GET THIS VERSION
$ git clone --branch v0.2.9 https://github.com/openai/openai-agents-python.git
# already have the repo? check out this version:$ git checkout v0.2.9
›Adds on_llm_start and on_llm_end lifecycle hooks to the agent, letting callers instrument or intercept LLM calls at the start and end of each invocation.
›Adds a context parameter to run_demo_loop, enabling callers to pass runtime context through the interactive demo loop.
›Adds a SQLAlchemy session backend for conversation history management, enabling persistent, database-backed storage of conversation state.
›Adds retry logic to MCP server operations, improving resilience when MCP servers are temporarily unavailable.
›Adds a realtime input timeout trigger event, surfacing a new event type when realtime session input exceeds a configured timeout.
+2 moreshow less
›Adds conditional tool enabling to agent-as-tool, allowing tools exposed via an agent to be selectively enabled or disabled at runtime.
›Adds a quick opt-in option to switch to the gpt-5 model.
Arize Phoenix 11.26.0 adds a timeline view for tracing.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v11.26.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v11.26.0
›Adds a timeline view for inspecting traces in the tracing UI.
$ git clone --branch arize-phoenix-v11.25.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v11.25.0
›get_spans_dataframe now sorts results by newest/oldest spans, enabling time-ordered span retrieval from the API.
›Adds eval and annotation quick filters to the experiments UI for faster result exploration.
›Helm chart now special-cases sqlite:///:memory: so in-memory SQLite deployments are handled correctly.
›Experiment compare list page now hydrates data for richer side-by-side comparisons.
›Disk usage notification emails now CC a support email address.
THE AI TOOLCHAIN