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 v1.2.2-vscode adds env support in config YAML, Sentry error tracking, Inception model support, and unsafe file read protection.
└──▷ GET THIS VERSION
$ git clone --branch v1.2.2-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout v1.2.2-vscode
└──▷ USE IT
Declare API keys or other environment variables directly in your Continue config file instead of relying on shell environment injection.
An open-source AI agent that brings the power of Gemini directly into your terminal.
gemini-cli v0.4.0-preview adds session recording, smart edits, fuzzy commands, --session-summary, extension linking, and more.
└──▷ GET THIS VERSION
$ git clone --branch v0.4.0-preview https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.4.0-preview
└──▷ TRY IT
Generate a session summary at the end of a long agentic run to capture what was done.
$ gemini --session-summary
Pass a prompt directly as a positional argument for quick, scriptable one-shot queries.
$ gemini 'Summarize the TODOs in this repo'
Link a locally developed extension into gemini-cli without publishing it.
$ gemini extensions link <path>
›Adds --session-summary flag to generate a summary at the end of a session.
›Integrates chat recording into GeminiChat via session recording support.
›Introduces a Smart Edit (replace) tool for more precise in-file edits aligned with the EditTool.
›Adds fuzzy matching for slash-command suggestions in the CLI.
›Adds gemini extensions link command to link local extensions by path.
+16 moreshow less
›Adds flag to update all extensions at once.
›Supports installing extensions using org/repo shorthand.
›Supports resolving environment variables in extension configuration.
›Adds Pro Quota Dialog to surface quota information to users.
›Shows citations at the end of each turn.
›Adds syntax highlighting for input /commands and @file/paths.
›Adds footer configuration settings.
›Supports nested .gitignore files for file filtering.
›Adds Ctrl+Backspace keyboard shortcut to delete a word backward.
›Adds enforcedAuthType setting to lock down authentication method.
›Adds MCP loading indicator when initializing the CLI.
›Skips MCP server connections in untrusted folders (folder trust enforcement).
›Adds positional argument support for passing a prompt directly on the command line.
›Simplifies MCP server timeout configuration.
›Merges general settings from multiple configuration sources.
gemini-cli v0.4.0-nightly adds extension management commands, --allowed-tools flag, YOLO/AUTO_EDIT lockout for untrusted folders, and subagent streaming.
└──▷ GET THIS VERSION
$ git clone --branch v0.4.0-nightly.20250904.e133acd2 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.4.0-nightly.20250904.e133acd2
└──▷ TRY IT
Run gemini non-interactively in CI without confirmation prompts for specific tools, reducing pipeline friction.
$ gemini --allowed-tools read_file,shell -p "Summarize all TODO comments in the repo"
›Adds extensions install command to install extensions from the CLI.
›Adds extensions uninstall command to remove installed extensions.
›Adds extensions list command to view installed extensions.
›Adds extensions update command to update installed extensions.
›Adds extensions enable and extensions disable commands to toggle extensions without uninstalling.
+17 moreshow less
›Adds initial set of extension variables for use within extensions.
›Adds --allowed-tools flag to bypass tool confirmation prompts for specified tools.
›Disables YOLO and AUTO_EDIT modes when operating in untrusted folders, preventing unattended destructive actions.
›Enables incremental output streaming for subagent tasks.
›Adds OIDC fallback to OAuth metadata lookup for MCP connections.
›Shares file list patterns between glob and grep tools, so filtering patterns apply consistently across both.
›Supports JSON Schema formats via ajv-formats for richer schema validation.
›Adds @file processing support in TOML commands.
›Adds session ID logging for non-interactive sessions in debug mode.
›Displays usage details in the /tools command output.
›Introduces system defaults (separate from system overrides) in configuration.
›Standardizes exit codes across CLI operations.
›Makes error messages more informative.
›Adds A2A-server package to gemini-cli.
›Adds OTel logging for MalformedJsonEvent events.
›Enables Firebase Studio as a supported IDE install target.
›Prompts users to migrate workspace extensions on upgrade.
└──▷ BREAKING ON UPGRADE
!The CLI flags all_files and show_memory_usage have been removed.
›Introduces ApprovalRequestMessage and ApprovalResponseMessage as two new LettaMessage types, enabling human-in-the-loop approval flows where agents request approval before executing tools and clients respond via client.agents.messages.create with type: 'approval', approve, and approval_request_id fields.
›Upgrades the Agent File (.af) schema to v2, adding support for groups (multi-agent) and files.
›Adds tag-based insert and search for archival memories, allowing agents to attach and query arbitrary string tags on memory entries.
›Adds timestamp-based temporal filtering for archival memory search.
›Adds a new archival search endpoint with hybrid search functionality.
+6 moreshow less
›Adds the ability to list and filter tools by type.
›Enables overriding the embedding config when importing an Agent File.
›Adds GPT-5 support with proper context window handling and reasoning effort configuration.
›Adds DeepSeek provider support via the new agent loop architecture.
›Enhances Anthropic provider support with native reasoning and improved tool schema formatting.
LlamaIndex v0.13.5 adds thinking delta in AgentStream events, system prompt/tool caching for BedrockConverse, and a YugabyteDB chat store.
└──▷ GET THIS VERSION
$ git clone --branch v0.13.5 https://github.com/run-llama/llama_index.git
# already have the repo? check out this version:$ git checkout v0.13.5
└──▷ USE IT
Stream an agent response and surface the model's thinking delta alongside the output token stream.
python
async for event in agent.astream_chat("Explain RSA encryption"):
if hasattr(event, 'thinking_delta') and event.thinking_delta:
print("[thinking]", event.thinking_delta)
if hasattr(event, 'delta') and event.delta:
print(event.delta, end="", flush=True)
Enable tool caching and a system prompt on a BedrockConverse LLM to reduce latency and token costs on repeated tool calls.
python
from llama_index.llms.bedrock_converse import BedrockConverse
llm = BedrockConverse(
model="anthropic.claude-3-5-sonnet-20241022-v2:0",
system_prompt="You are a security analyst assistant.",
tool_caching=True,
)
›Adds thinking_delta field to AgentStream events in llama-index-core to expose thinking deltas from LLM responses.
›Adds system prompt and tool caching config kwargs to BedrockConverse in llama-index-llms-bedrock-converse.
›New llama-index-storage-chat-store-yugabytedb package (v0.1.0) introduces a YugabyteDB-backed chat store.
Phoenix 11.32.0 paginates experiment runs and improves the experiment list UI.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v11.32.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v11.32.0
›Paginates experiment runs inside run_experiment to support large experiment datasets without memory pressure.
›Improves the experiments list page UI with frontend enhancements for browsing experiments.
Phoenix client v1.18.0 adds pagination to run_experiment when fetching experiment runs.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-client-v1.18.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-client-v1.18.0
›Adds pagination support to run_experiment when retrieving experiment runs, enabling use with large experiment datasets.
LanceDB python-v0.25.0 adds multi-level namespace support, named indices, and PyTorch __getitems__ integration.
└──▷ GET THIS VERSION
$ git clone --branch python-v0.25.0 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:$ git checkout python-v0.25.0
└──▷ USE IT
Define a named IVF-PQ index without triggering training immediately, useful when you want to stage index creation in a pipeline.
›Adds train=False parameter to index creation calls, allowing indices to be defined without immediately training them.
›Adds name parameter to all Python create_index calls so indices can be created and referenced by a user-defined name.
›Supports multi-level namespaces for organizing tables and databases hierarchically, with full Python SDK integration via lance namespace.
›Adds __getitems__ method to enable native PyTorch dataset integration for batch item retrieval.
›Upgrades lance to 0.33.0-beta.3, pulling in upstream performance and capability improvements.
└──▷ BREAKING ON UPGRADE
!Multi-level namespace support changes how namespaces are addressed; existing single-level namespace usage may need updates to conform to the new hierarchy model.
THE AI TOOLCHAIN