Backfill issue -203 — 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   # 7 tools matched

AI & LLM Tooling

◆ AI Agent Frameworks

Agno (formerly Phidata)

v2.4.5 2 RELEASES · 2026-01-26 NOTES STABLE

Agno v2.4.5 adds Seltz Search toolkit and a new parameter to suppress knowledge search instructions in system prompts.

└──▷ GET THIS VERSION

$ git clone --branch v2.4.5 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:
$ git checkout v2.4.5

└──▷ USE IT

Suppress auto-injected knowledge search instructions in the system prompt when you want full control over prompt content.

python

from agno.agent import Agent

agent = Agent(
    knowledge=my_knowledge_base,
    add_search_knowledge_instructions=False,
)
agent.run('What are our internal policies on data retention?')

Equip an agent with Seltz Search to let it query the Seltz search engine during reasoning.

python

from agno.agent import Agent
from agno.tools.seltz import SeltzTools

agent = Agent(
    tools=[SeltzTools()],
)
agent.run('Find recent research on LLM reasoning benchmarks.')

›Adds add_search_knowledge_instructions parameter to Agent and Team classes to control whether knowledge search instructions are injected into the system prompt.
›New SeltzTools toolkit integrating Seltz Search as a tool source for agents.

1 more release in this issue · 2026-01-26

v2.4.4 NOTES STABLE

Agno v2.4.4 adds UnsplashTools image search, Moonshot model provider, and a new external_execution_silent tool decorator param.

└──▷ GET THIS VERSION

$ git clone --branch v2.4.4 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:
$ git checkout v2.4.4

└──▷ USE IT

Give an agent access to high-quality royalty-free images from Unsplash for content generation or research workflows.

python

from agno.tools.unsplash import UnsplashTools

agent = Agent(tools=[UnsplashTools()], ...)

›Adds external_execution_silent parameter to the tool decorator to suppress placeholder strings from run response content during external tool execution.
›Adds UnsplashTools toolkit for searching and retrieving royalty-free images via the Unsplash API.
›Adds Moonshot (moonshot.ai) as a new model provider.

Was this useful?

camel-ai

v0.2.85 NOTES

camel-ai v0.2.85 adds Zhipu GLM 4.1V-thinking, 4.5, 4.6, and 4.7 model support

└──▷ GET THIS VERSION

$ git clone --branch v0.2.85 https://github.com/camel-ai/camel.git
# already have the repo? check out this version:
$ git checkout v0.2.85

›Adds support for Zhipu's GLM-4.1V-thinking, GLM-4.5, GLM-4.6, and GLM-4.7 models.

Was this useful?

◆ AI Coding Agents

Continue

@continuedev/[email protected] NOTES

Continue CLI gains automatic WSL detection to spawn the appropriate shell environment.

└──▷ 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]

›CLI automatically detects WSL environments and spawns the appropriate shell.

Was this useful?

GitHub Copilot CLI

v0.0.395 NOTES

GitHub Copilot CLI v0.0.395 adds /mcp show server visibility, plugin skill execution, and line-specific /diff commenting.

└──▷ GET THIS VERSION

$ git clone --branch v0.0.395 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.395

›Adds /mcp show command to display all configured MCP servers, including defaults, servers from additional configuration, and servers from installed plugins.
›Adds commenting to /diff mode for line-specific feedback.
›Plugin skills are now usable by the agent in sessions.
›Loads local shell configuration in agent sessions.
›Completed tool calls now display in prompt mode.

Was this useful?

Earendil Works Pi

v0.50.0 NOTES

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Pi v0.50.0 adds package management, custom providers, Azure OpenAI Responses, hot reload, and a new --verbose flag.

└──▷ GET THIS VERSION

$ git clone --branch v0.50.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.50.0

└──▷ TRY IT

Reload all skills, themes, and extensions mid-session after editing them on disk.

$ /reload

Start Pi with full startup diagnostics visible, overriding a quiet-startup config.

$ pi --verbose

›New pi install, pi remove, pi update, and pi list commands for managing extension packages (npm/git sources).
›New pi config TUI command to enable/disable package and top-level resources via glob patterns.
›New /reload command for hot-reloading extensions, skills, prompts, themes, and context files without restarting.
›Custom provider registration via pi.registerProvider() for proxies, OAuth/SSO flows, and non-standard streaming APIs.
›Adds azure-openai-responses provider supporting the Azure OpenAI Responses API with deployment-aware model mapping.

+12 moreshow less

›Adds OpenRouter routing support for custom models via the openRouterRouting field in model config.
›New --verbose CLI flag to override the quietStartup setting and show full startup output.
›New CLI flags --skill, --prompt-template, --theme, --no-prompt-templates, and --no-themes for resource selection at launch.
›Skill invocation messages are now collapsible in chat output, shown collapsed by default.
›Header values in models.json now support environment variable and shell command resolution, matching apiKey behavior.
›Glob pattern support (minimatch) in package filters, top-level settings arrays, and pi manifests.
›New markdown.codeBlockIndent setting to customize code block indentation in rendered output.
›HTTP proxy environment variable support for all API requests.
›Session renaming directly from the /resume picker via Ctrl+R.
›Session selector keybindings are now fully configurable.
›Footer now shows the active provider alongside the model when multiple providers are available.
›Exposes copyToClipboard utility for use by extensions.

└──▷ BREAKING ON UPGRADE

!Header values in models.json now resolve environment variables: if a literal header value matches an env var name, the env var's value is used instead, which may change behavior for existing configs.
!External packages (npm/git) are now configured via the packages array in settings.json instead of extensions; existing npm:/git: entries in extensions are auto-migrated.
!Resource loading now uses ResourceLoader only and settings.json uses arrays for extensions, skills, prompts, and themes.
!discoverAuthStorage and discoverModels are removed from the SDK; AuthStorage and ModelRegistry now default to ~/.pi/agent paths unless you pass an agentDir.
!The /resume picker sort toggle is moved from Ctrl+R to Ctrl+S (freeing Ctrl+R for session rename).

Was this useful?

Alibaba Qwen Code

v0.8.0-nightly.20260126.829ba9c4 NOTES

Qwen Code v0.8.0 adds a /bug command in non-interactive mode, an extension system with a detail subcommand, and a redesigned CLI welcome screen.

└──▷ GET THIS VERSION

$ git clone --branch v0.8.0-nightly.20260126.829ba9c4 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.8.0-nightly.20260126.829ba9c4

└──▷ TRY IT

Inspect details and validation status of a loaded extension.

$ qwen extensions detail <extension-name>

›Adds /bug command availability in non-interactive (pipeline/scripted) mode.
›Introduces an extensions subsystem (Feat/extension) with an extensions detail subcommand and improved extension validation.
›Adds runtime-aware fetch options for Anthropic and OpenAI providers, enabling provider-specific network configuration at runtime.
›Redesigns the CLI welcome screen and settings dialog.
›Uses dim colors for YOLO/auto-accept mode borders, visually distinguishing that mode in the terminal UI.

+1 moreshow less

›Switches token counting from the local tiktoken dependency to API-reported token counts.

Was this useful?

Other / Uncategorized

◆ VECTOR DB RAG

LanceDB

python-v0.27.1 2 RELEASES · 2026-01-26 NOTES STABLE

LanceDB python-v0.27.1 adds AZURE_STORAGE_ACCOUNT_NAME environment variable support for remote connections.

└──▷ GET THIS VERSION

$ git clone --branch python-v0.27.1 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout python-v0.27.1

›Reads the AZURE_STORAGE_ACCOUNT_NAME environment variable when establishing remote Azure Storage connections, removing the need to pass the account name explicitly in code.

1 more release in this issue · 2026-01-26

v0.24.1 NOTES STABLE

LanceDB v0.24.1 adds AZURE_STORAGE_ACCOUNT_NAME environment variable support for remote connections.

└──▷ GET THIS VERSION

$ git clone --branch v0.24.1 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout v0.24.1

›Reads the AZURE_STORAGE_ACCOUNT_NAME environment variable when establishing remote Azure Storage connections, removing the need to hard-code the account name.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · January 26, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -203, January 26, 2026

Agno (formerly Phidata)

camel-ai

Continue

GitHub Copilot CLI

Earendil Works Pi

Alibaba Qwen Code

LanceDB