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 v2.2.4 adds num_history_messages for granular history control and AgentOS access in lifespan functions
└──▷ GET THIS VERSION
$ git clone --branch v2.2.4 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:$ git checkout v2.2.4
└──▷ USE IT
Limit history context to the last 5 messages to reduce token usage in long-running conversations.
python
agent = Agent(
...
num_history_messages=5,
)
›Adds num_history_messages parameter to control how many messages are considered when retrieving agent history.
›Enables access to the contextual AgentOS instance within FastAPI lifespan functions, allowing updates to the instance after initialization and first run.
›Supports Media instances when providing run input as a dictionary (in addition to a list of Message objects).
AutoGPT Platform v0.6.35 adds agent execution in the new builder and cascading stop for nested graph executions.
└──▷ GET THIS VERSION
$ git clone --branch autogpt-platform-beta-v0.6.35 https://github.com/Significant-Gravitas/AutoGPT.git
# already have the repo? check out this version:$ git checkout autogpt-platform-beta-v0.6.35
›Adds agent execution functionality directly in the new builder UI.
›Standardizes error handling across blocks with new BlockSchemaInput and BlockSchemaOutput base classes.
›Increases max_field_size in aiohttp requests to support larger payloads.
›Adds cost configurations for Revid video blocks.
└──▷ BREAKING ON UPGRADE
!Claude 3.5 Sonnet and Haiku models have been removed from the platform.
LlamaIndex v0.14.7 adds SerpEx tool, GitHub App auth, Bedrock Guardrails streaming, and tool-call-block support for Anthropic, MistralAI, and Ollama.
└──▷ GET THIS VERSION
$ git clone --branch v0.14.7 https://github.com/run-llama/llama_index.git
# already have the repo? check out this version:$ git checkout v0.14.7
›Adds llama-index-tools-serpex (v0.1.0), a new SerpEx search tool integration for agent pipelines.
›Adds streamProcessingMode support for Bedrock Guardrails in llama-index-llms-bedrock-converse, enabling streaming-compatible guardrail enforcement.
›Adds optional streamProcessingMode for Bedrock structured output (previously forced), giving callers control over when it is applied.
›Adds GitHub App authentication support to llama-index-readers-github (v0.9.0), complementing existing token-based auth.
›Integrates tool-call-block support into llama-index-llms-anthropic (v0.10.0), llama-index-llms-mistralai (v0.9.0), and llama-index-llms-ollama (v0.9.0) for structured tool-use responses.
+5 moreshow less
›Updates llama-index-embeddings-voyageai (v0.5.0) with the latest VoyageAI integration.
›Adds Hyperscale and Composite Vector Index support to llama-index-vector-stores-couchbase (v0.6.0).
›Makes SVG processing optional in llama-index-readers-confluence (v0.5.0), removing the hard pycairo install requirement.
›Updates available models in llama-index-llms-fireworks (v0.4.5).
›Allows setting the temperature parameter for gpt-5-chat in llama-index-llms-openai (v0.6.6).
Lightweight coding agent that runs in your terminal
Codex CLI v0.52.0 adds shell passthrough with !<cmd>, TUI undo, configurable compaction prompt, keyring auth, and MCP OAuth scopes.
└──▷ GET THIS VERSION
$ git clone --branch rust-v0.52.0 https://github.com/openai/codex.git
# already have the repo? check out this version:$ git checkout rust-v0.52.0
└──▷ TRY IT
Run a quick shell command mid-session without leaving the Codex prompt — useful for checking git status or running a build before your next instruction.
$ !git status
›Adds !<cmd> syntax to execute shell commands directly from the Codex prompt.
›New TUI undo operation lets users roll back the last applied change.
›Queued messages are now visible in the TUI during active response streaming.
›Compaction prompt is now configurable by the user.
›New auth storage abstraction with OS keyring support and configurable backend.
+15 moreshow less
›Adds MCP OAuth scope specification support via mcp add.
›MCP tool call results that include images are now rendered to the model.
›Environment variable values are redacted in /mcp and mcp get output.
›New GetConversationSummary RPC enables fetching and resuming conversation summaries by ID.
›Item streaming events added to the app-server protocol.
›Sandbox policy violations now surface a model summary and risk assessment.
›Adds sandbox_mode support in user profiles.
›MIME type verification added for attached images.
›Windows TUI now displays auto-mode setup guidance.
›Conversations annotated with model_provider field to enable filtering.
›Ability to purchase credits for additional usage surfaced in the CLI.
›MCP startup errors for timeouts and GitHub auth now provide clearer messaging.
›Local tokenizer used for accurate truncation of unified exec tool outputs.
›Stale or missing rate-limit data now produces explicit messaging in the TUI.
›Returns an error when an unknown feature flag is passed to enabled/disabled feature config.
An open-source AI agent that brings the power of Gemini directly into your terminal.
gemini-cli v0.13.0-nightly adds a config-based policy engine, extension explore subcommand, keychain-stored extension settings, and response recording for testing.
└──▷ GET THIS VERSION
$ git clone --branch v0.13.0-nightly.20251030.42c79c64 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.13.0-nightly.20251030.42c79c64
└──▷ TRY IT
Record live model responses during a session so they can be replayed deterministically in tests.
$ gemini --record-responses
Discover the tools and capabilities exposed by an installed extension without starting a full chat session.
$ gemini extension explore
›New config-based policy engine with TOML configuration for enforcing tool confirmation guards via message bus settings.
›New explore subcommand for extensions, enabling discovery of extension capabilities from the CLI.
›Adds support for sensitive, keychain-stored per-extension settings to protect extension credentials.
›New --record-responses flag to record model responses for use in testing workflows.
›Adds OpenTelemetry-compliant semantic standard logging, including dev OTEL trace instrumentation and a Genkit telemetry/dev UI setup script.
+4 moreshow less
›Granular memory loaders implemented for JIT (just-in-time) architecture in core.
›Improved API key authentication flow for a smoother onboarding experience.
›Debug drawer keybinding changed to F12.
›Adds auth_type and loaded extensions to StartSessionEvent OTel telemetry for richer session observability.
THE AI TOOLCHAIN