Changelog

What's new in GoClaw

v0.1.21

MCP Client & Smarter Cron Silence

GoClaw can now connect to external MCP servers and use their tools as if they were built in — configure a server, and its tools show up in your role permissions automatically. Cron jobs that should stay silent are also more reliable now, even when models get chatty.

New Features

  • MCP Client Support

    Connect GoClaw to any MCP server — remote over HTTP or local via subprocess — and their tools appear as regular GoClaw tools. Access is controlled through the existing role system, and you can filter which tools to import per server with allow/deny lists. Manage connections live with /mcp or the HTTP dashboard.

    Documentation →
  • /mcp Command

    New owner-only command to check server connection status, list registered tools, and reconnect a server without restarting GoClaw.

    Documentation →

Improvements

  • Cron Silence Handling

    Silent responses from cron jobs now work reliably even when the model appends extra text before SILENT_OK. Previously this could leak internal narration into your chat — now the entire response is suppressed as intended.

v0.1.20

Background Delegation, Account Login & /btw

GoClaw's agent can now hand off coding work to Cursor or Grok in the background and keep chatting with you while it runs — you can ask what it's doing at any time. You can also log in with your xAI or OpenAI account instead of pasting API keys, and ask quick side questions to a working agent without derailing it.

New Features

  • Background ACP Delegation

    GoClaw's agent can start a coding task on an attached Cursor or Grok session and stay responsive while it works. Live progress streams into your chat, and GoClaw reports status when you ask. When the coding agent finishes, GoClaw picks up automatically.

    Documentation →
  • /btw Side Questions

    Ask the attached ACP agent a quick question without breaking its flow. /btw interrupts, answers with full context, then the agent resumes what it was doing.

    Documentation →
  • Account Login (Auth Profiles)

    Sign in with your xAI or OpenAI account instead of managing API keys. GoClaw stores tokens encrypted and the xAI image, video, and search tools reuse the same login. Set up via device code (great for headless servers) or browser OAuth.

    Documentation →

Improvements

  • Inline Provider Login in Setup Editor

    The config editor now runs the entire login flow inline — pick auth method, start login, paste code, done. No need to leave the editor or juggle browser tabs separately.

  • Immediate Cancellation

    Cancelled or timed-out agent runs now stop right away instead of being misread as slow-provider timeouts. Deadlines are honored promptly and stuck runs can't keep burning models past their budget.

  • Cron Stale-Run Auto-Reap

    Jobs that crash mid-run no longer appear stuck 'running' forever. GoClaw clears leaked running flags automatically after a configurable ceiling (default 30 minutes).

    Documentation →
  • Browser Private Networks

    New allowPrivateNetworks option lets the browser reach LAN devices (like a local Home Assistant) when enabled. Loopback and cloud-metadata addresses stay blocked.

    Documentation →
  • Shadow DOM Selector Piercing

    CSS selectors in the browser tool now automatically reach inside Shadow DOM (Web Components) without extra steps.

    Documentation →
v0.1.19

Grok ACP Driver & Self-Hosted Updates

GoClaw can now drive Grok Build sessions alongside Cursor — attach to whichever agent fits the task. The installer and self-updater have moved to goclaw.org so updates keep flowing without GitHub. Error handling for xAI models is also smarter: fewer false alarms, better failover.

New Features

  • Grok ACP Driver

    Attach to xAI's Grok Build CLI as an ACP session, just like Cursor. Pick your driver per attach or set a default. Grok is now the default driver — switch back with /acp attach cursor or change acp.defaultDriver in config.

    Documentation →
  • ACP Context Badge

    While an ACP session is attached, the HTTP chat header shows live token usage from the agent — including context window percentage, active model, and session state.

    Documentation →
  • Agent Slash Command Routing

    Slash commands the attached agent advertises (like /compact or /help) now go to the agent instead of GoClaw. You always keep /acp, /a2a, and /shutdown locally.

    Documentation →

Improvements

  • Installer Moved to goclaw.org

    The install script and self-updater now pull releases from git.goclaw.org. Existing 0.1.18 installs self-update automatically; older installs need a one-time reinstall via curl -fsSL https://goclaw.org/install.sh | sh.

    Documentation →
  • Smarter xAI Error Handling

    Models that don't support reasoning effort no longer trigger a misleading 'session corrupted' error — GoClaw retries without it automatically. Backend errors also fail over to the next model instead of killing the conversation.

  • Grok Status Notices

    When Grok retries a failing API call, a subtle status notice appears in HTTP, TUI, and Telegram so you know it's working on it. Rich error messages replace the generic JSON-RPC codes.

    Documentation →
  • Quieter Networking Logs

    Routine libp2p rendezvous and address-list chatter stays out of INFO logs. Real connectivity changes still surface.

v0.1.17

Send Anything from Telegram and WhatsApp

Videos, documents, audio, stickers — Telegram and WhatsApp now accept them all. No more silent drops. Plus better PDF extraction with smarter OCR and cleaner output.

New Features

  • Full Upload Support

    Send documents, videos, audio files, stickers, and animations from Telegram or WhatsApp. They're saved permanently and the agent can work with them.

    Documentation →

Improvements

  • Better PDF Extraction

    Hyphenated words no longer break across lines. Scanned pages inside text PDFs get OCR'd automatically. Decorative logos and rules are filtered out.

    Documentation →
  • Smarter Image Captions

    Embedded images now use surrounding document context for better descriptions. DOCX footnotes, HTML images, and Excel pictures all come through.

    Documentation →
  • Permanent Uploads

    Voice notes and images from Telegram and WhatsApp are no longer pruned by media cleanup. Your files stick around.

    Documentation →
v0.1.16

Document Extraction and Smart Reminders

Send GoClaw a PDF, Word doc, or e-book and it reads the whole thing for you. Routines now fire on schedule and can nudge you at the right time across all your channels.

New Features

  • Read Any Document

    Upload PDFs, Word docs, spreadsheets, or e-books and GoClaw extracts the text automatically. Scanned pages get OCR. No more copy-pasting.

    Documentation →
  • Scheduled Reminders

    Routines like 'gym with Bob every Tuesday at 6pm' now wake the agent at the right time. It can nudge you, stay quiet, or take action — your choice.

    Documentation →
  • Today's Schedule

    Your daily bulletin now shows what's coming up, with clear markers when something was skipped or handled silently.

    Documentation →

Improvements

  • Smarter Routine Storage

    Recurring events now take structured fields — days, times, location, person — instead of hoping the agent parses your prose correctly.

    Documentation →
  • Trigger Audit Log

    Ask 'did you remind me about that?' and get a real answer. The agent can check what fired, what was silent, and what got missed.

    Documentation →

Documentation

  • Document Extract Guide

    New docs covering supported formats, OCR, caching, and vision chain behavior.

  • Memory Graph Updates

    Expanded docs for recurring routines, trigger inspection, and the Today's Schedule bulletin.

v0.1.15

Lossless Context Management

GoClaw now remembers long conversations. When the chat outgrows the context window, older parts are rolled up into searchable summaries instead of being dropped. The agent can drill back into the original messages whenever it needs the detail.

New Features

  • Lossless Context Management (LCM)

    Compacted history is now stored as searchable summaries linked to the raw messages they covered. Use grep_summaries, describe, and expand to recover details from months ago.

    Documentation →
  • Recall Presets

    Four presets — balanced, aggressive, long_term_memory, and recall_heavy — control how much history GoClaw carries forward. Configure under session.summarization.compaction.lcm.preset.

    Documentation →
  • transcript.stats Agent Tool

    The agent can now inspect its own recall state, DAG health, and get preset-tuning hints through the transcript tool's stats action.

    Documentation →

Improvements

  • Automatic Catch-Up

    Existing installs with large chat histories catch up automatically after upgrade. /session shows the progress while it runs.

    Documentation →
  • Budget-Fit Summary Injection

    Prompts now include a non-overlapping frontier of compacted summaries that fits the configured token budget, with newer summaries prioritized.

    Documentation →

Documentation

  • Session Management Rewrite

    Comprehensive docs covering LCM architecture, presets, condensation, recall tools, and configuration reference.

  • Transcript Search Guide

    Updated transcript search docs with grep_summaries, describe, and expand action examples for compacted history recall.

v0.1.14

A2A Networking, Local LLMs, and Expanded Cursor ACP

GoClaw can now talk to other GoClaw nodes over the internet and run models locally without external providers. A2A networking uses libp2p with relay fallback and NAT traversal. Local LLM management downloads, configures, and runs llama.cpp models with prompt caching.

New Features

  • A2A Peer Networking

    Send tasks to remote GoClaw nodes over libp2p. Includes rendezvous discovery, relay-first connectivity with automatic direct upgrades, and NAT traversal. Use /a2a commands or let the agent handle it.

    Documentation →
  • Agent A2A Tool

    The agent can inspect peer state, ping nodes, submit tasks, and manage remote work through a native a2a tool. Owner-only access.

    Documentation →
  • Local LLM Management

    Run models locally with managed llama.cpp. GoClaw handles model downloads, server lifecycle, prompt caching, and hardware detection. Setup editors guide you through model selection.

    Documentation →
  • A2A Peer Management in Web UI

    Add, edit, and test A2A peers from the live web interface. See local pairing info, ping peers, and manage trust records without touching config files.

    Documentation →

Improvements

  • llama.cpp Prompt Caching

    Managed llama.cpp servers now pin conversations to stable slots for better prompt cache reuse across turns.

    Documentation →
  • Curated Local Model Catalog

    Qwen3 Coder variants added to the managed model list at various quantization levels. Text-only models no longer require a vision sidecar.

    Documentation →
  • Background Direct Upgrades

    A2A connections that start via relay can upgrade to direct paths in the background without delaying live traffic.

    Documentation →
  • Cursor ACP Session Handling

    Expanded Cursor ACP integration with better startup, session management, and interactive prompt plumbing.

    Documentation →

Documentation

  • A2A Networking Guide

    New dedicated docs covering A2A setup, peer pairing workflow, configuration reference, troubleshooting, and agent tool usage.

v0.1.12

ACP Configuration Section, Setup Editors, and Dashboard Shortcuts

GoClaw 0.1.12 adds a dedicated ACP config section with setup editor support, live Cursor model refresh, and new dashboard shortcuts for Coding Agents and Web Search.

New Features

  • Dedicated ACP Configuration Section

    Cursor ACP preferences now live under a top-level `acp` config section with browser and TUI setup editor support.

    Documentation →
  • Live Cursor Model Refresh

    Setup editors now include a Refresh Cursor Models action to rebuild the in-memory model catalog for the dropdown without restarting.

    Documentation →
  • Dashboard Shortcuts for Coding Agents and Web Search

    The setup web UI adds quick-task dashboard cards for Coding Agents and Web Search with deep-link expansion into relevant config sections.

    Documentation →

Improvements

  • Legacy ACP Config Migration

    Existing `gateway.acpCursorModel` values are automatically migrated to the new `acp.drivers.cursor.model` path.

    Documentation →
  • Workspace Template Self-Heal

    Onboarding now creates missing workspace templates and avoids recreating `BOOTSTRAP.md` once `SOUL.md` exists.

    Documentation →

Documentation

  • ACP and Configuration Docs Refresh

    Docs updated to reflect the new ACP config structure, setup editor behavior, and model refresh actions.

v0.1.11

Cursor ACP Sessions and Interactive Prompt Handling

GoClaw 0.1.11 adds Cursor coding agent integration via ACP, with interactive prompts surfaced across HTTP, Telegram, and TUI channels.

New Features

  • Cursor ACP Sessions

    Connect Cursor's coding agent to your GoClaw session via local stdio. Prompts, plans, and tool activity flow through your existing channels.

    Documentation →
  • Agent-Facing ACP Tools

    New acp_attach, acp_info, acp_respond, and acp_cancel tools let the agent manage ACP sessions directly.

    Documentation →
  • Interactive Prompts Across Channels

    Cursor asks, plans, to-dos, and image requests appear in HTTP chat, Telegram, and TUI with shared handoff and cancellation handling.

    Documentation →
  • Telegram Poll Handling

    Multi-select prompts render as native Telegram polls with an escape hatch for custom answers.

    Documentation →

Documentation

  • ACP Guides

    New operator and tool reference docs for Cursor attachment, session scoping, and agent ACP workflows.

v0.1.10

Script-friendly status, restart helper, and clearer installer guidance

GoClaw 0.1.10 makes automation around installs and operations easier: structured status output for scripts, a small restart command for the daemon, and installer messaging that better matches already-configured and already-running setups.

Improvements

  • Script-Friendly Status and Restart

    goclaw status --field provides shell-safe, structured output including a clear configured=false path when no config exists yet; goclaw restart offers a simple daemon restart helper.

    Documentation →
  • Installer Update Guidance

    Post-install messaging better distinguishes already-configured and already-running installs and trims brittle shell parsing in the install script.

    Documentation →
v0.1.9

0.1.9 TUI Onboarding Flow Alignment and Setup Validation

This 0.1.9 follow-up aligns TUI onboarding flow with the browser wizard, improves step progression and validation behavior, and tightens setup requirements around channel, provider, and voice configuration.

Improvements

  • TUI Onboarding Step Flow Aligned with Browser Wizard

    TUI onboarding now follows the same communication-channel, pairing, provider, and review progression as the browser setup experience for a more consistent operator workflow.

    Documentation →
  • Dynamic Step Management for Conditional Setup Paths

    Wizard step handling now supports conditional step insertion/removal while preserving user position, improving behavior when setup choices change mid-flow.

    Documentation →
  • Unified Channel Configuration Entry Point

    Telegram and WhatsApp enablement now live in a consolidated communication-channels step with clearer gating into pairing.

    Documentation →
  • Expanded Voice and STT Onboarding Controls

    Voice settings and STT readiness checks were integrated more directly into TUI onboarding, including model-availability and API-key validation paths.

    Documentation →

Bug Fixes

  • Preset Warning Acknowledgement Enforcement

    Setup now requires explicit preset warning acknowledgement before advancing, preventing accidental progression past important sandbox warnings.

  • Required Setup Field Validation Before Step Exit

    Wizard exit checks now enforce required fields for enabled channels and selected providers, reducing incomplete setup saves.

v0.1.9

Channel Pairing in Setup, Installer Guidance, and 0.1.9 Security Updates

GoClaw 0.1.9 adds first-class Telegram and WhatsApp owner pairing in setup flows, improves setup UX and install guidance for new versus existing installs, and includes a security dependency bump.

New Features

  • Built-In Telegram and WhatsApp Owner Pairing

    Setup flows now support direct owner pairing for Telegram and WhatsApp across browser and TUI onboarding/edit modes, with staged identity data saved when setup is completed.

    Documentation →
  • Channel Pairing Backends for Setup

    GoClaw now includes dedicated pairing backends for Telegram one-time-code validation and WhatsApp QR linking to support guided owner setup.

    Documentation →

Improvements

  • Setup UI Pairing Guidance and Validation

    Setup screens now make unpaired channels more visible and improve blocked-next guidance so operators can resolve pairing prerequisites earlier.

    Documentation →
  • Installer Guidance for New vs Existing Installs

    The installer now detects existing binaries/configs and suggests the right next step (`goclaw onboard` for guided setup or `goclaw setup edit` for existing configs).

    Documentation →
  • Onboarding Command Docs Refresh

    Docs now guide fresh setup through `goclaw onboard` while keeping `goclaw setup` and `goclaw setup edit` paths explicit for existing environments.

    Documentation →

Bug Fixes

  • Security Dependency Bump

    Upstream dependencies now include `golang.org/x/image` v0.38.0 to address the reachable TIFF decoding vulnerability identified during audit checks.

Documentation

  • Configuration and Runtime Behavior Clarifications

    Documentation updates clarify setup pairing behavior, installation flow, and additional web chat/runtime details in the latest release.

v0.1.8

Media Tooling, Voice Effects Controls, and Structured Memory Scheduling

GoClaw 0.1.8 adds an agent-facing media inspection tool, expands voice effects configuration in the web setup flow, and upgrades memory graph workflows with structured scheduling and stricter real-time memory-formation guidance.

New Features

  • New `media` Tool for Storage Visibility

    Agents can now inspect live media store usage, quotas, retention policies, and category warnings before generating, downloading, or storing large files.

    Documentation →
  • Structured Memory Scheduling with `happens_at`

    Memory graph now supports structured future scheduling fields and upcoming-event handling in query and bulletin flows for deadlines, appointments, and plans.

    Documentation →
  • Voice Effects Presets and Custom Controls

    VoiceLLM setup now includes richer effect controls and presets in the web config path, including parity for custom ring/bitcrush tuning.

    Documentation →

Improvements

  • Category-Aware Media Retention and Quotas

    Media configuration now exposes category-specific TTL and quota controls, global limits, and cleanup behavior with clearer storage policy guidance.

    Documentation →
  • Required Real-Time Memory Formation Workflow

    Agent memory guidance now explicitly requires completing recall/store decision workflows before final user responses when memory-worthy information is detected.

    Documentation →
  • Memory Query and Bulletin Timing Clarity

    Memory query and bulletin behavior now better surfaces scheduled items and distinguishes observed-time versus scheduled-time semantics.

    Documentation →

Documentation

  • 0.1.8 Docs Refresh Across Tools and Configuration

    Docs were updated across media, memory, configuration, and voice pages to reflect the 0.1.8 runtime changes and operational defaults.

v0.1.7

Browser Remote Profiles, Capture Controls, and 0.1.7 Runtime Refinements

GoClaw 0.1.7 expands browser automation with remote CDP profiles, capture/tracing/emulation actions, and MCP-style aliases, while improving memory extraction coordination and delegated-run reliability signals.

New Features

  • Named Remote CDP Browser Profiles

    Browser automation now supports named remote CDP profiles, host allowlists, and optional HTTP discovery for connecting to trusted Chrome instances on other machines.

    Documentation →
  • Browser Capture, Tracing, and Emulation Actions

    The browser tool now exposes console/network capture inspection, performance tracing and metrics, plus page-level viewport/device/CPU/network emulation controls.

    Documentation →
  • Expanded Browser Action Surface

    Browser actions now include drag support and MCP-style action aliases to improve interoperability with MCP-oriented prompts and workflows.

    Documentation →

Improvements

  • Memory Graph Extraction Coordination

    Memory extraction now coordinates agent-driven and background extraction with a configurable handoff delay to reduce overlap and improve ingestion timing.

    Documentation →
  • Runner and Fanout Reliability Signals

    Subagent fanout now reports partial-failure outcomes more explicitly and avoids producing optional extra summaries when worker outcomes are unhealthy.

    Documentation →
  • Runners Web UI Stability

    Runners web UI behavior was stabilized with improved live update handling and split-pane detail/transcript inspection ergonomics.

    Documentation →

Bug Fixes

  • OpenAI Next Driver Phase Parameter

    A regression around the `phase` parameter handling in the OpenAI-next driver path was fixed.

Documentation

  • Browser Documentation Refresh

    Browser docs were updated to cover remote profiles, capture/tracing, emulation, and alias behavior for the expanded browser tooling.

v0.1.6

Subagent Documentation Refined for Clarity

This docs refresh simplifies subagent and delegated-run terminology across concepts, tools, roles, and configuration so operators can understand behavior and controls more quickly.

Improvements

  • Clearer Subagent vs Delegated Terminology

    Core docs now use simpler subagent-first language while keeping delegated-run internals in context, reducing ambiguity in everyday usage.

    Documentation →
  • Configuration Guidance Tightened

    Configuration reference now explains `tools.subagent` and `gateway.delegatedRuns` dependencies and run-limit settings in more practical, user-facing wording.

    Documentation →
  • Tool Behavior Notes Simplified

    Tool reference for `subagent_spawn`, `subagent_fanout`, `subagent_status`, and `subagent_cancel` now focuses on operational behavior instead of deep implementation details.

    Documentation →

Documentation

  • Role Access Rules Clarified

    Role docs now more directly explain owner-only subagent access and why role allowlists alone cannot grant delegated-run control to non-owner users.

v0.1.6

Delegated Subagents, Fanout Runs, and Runner Visibility

GoClaw 0.1.6 introduces delegated subagent execution with fanout orchestration, a runners dashboard/API surface, and stronger visibility controls across HTTP, Telegram, and TUI flows.

New Features

  • Delegated Subagent and Fanout Execution

    New delegated-run tooling adds `subagent_spawn`, `subagent_fanout`, `subagent_status`, and `subagent_cancel` workflows for background and parallel subagent orchestration.

    Documentation →
  • Runner Registry and Return Routing

    Delegated runs now track lineage and completion through a dedicated runner registry with return routing, cancellation flow, and persisted run metadata.

    Documentation →
  • Runners Web UI and APIs

    A dedicated runners page and API endpoints now expose delegated-run status, run details, and event streams for operator visibility and control.

    Documentation →

Improvements

  • Delegated Run Visibility in Telegram and TUI

    Telegram and TUI messaging now provide clearer delegated-run progress and completion visibility, improving follow-up and multi-run monitoring.

    Documentation →
  • Delegated Runs Configuration Rollout

    Configuration docs now cover delegated-run limits, enablement flags, and subagent model/runtime controls under gateway and tools settings.

    Documentation →
  • Roles and Tooling Access Clarifications

    Role and tools documentation now explicitly describes delegated/subagent tool behavior, ownership scope, and operational guardrails.

    Documentation →
v0.1.5

Multi-Provider Web Search and Better Telegram/HTTP UX

GoClaw now supports multiple `web_search` backends with retry/fallback controls, improves Telegram delivery for long and structured responses, and refines HTTP chat tool-panel behavior.

New Features

  • Multi-Provider `web_search`

    `web_search` now supports `grok`, `brave`, `perplexity`, and `gemini` via a shared provider interface, including provider-aware result metadata.

    Documentation →
  • Search Retry and Fallback Controls

    Web search now supports configurable retry/backoff and provider fallback chains so transient upstream failures can recover automatically.

    Documentation →

Improvements

  • Expanded Web Search Configuration Surface

    Configuration and setup forms now expose provider selection, fallback ordering, retry tuning, and per-provider API key fields, while preserving legacy Brave key compatibility.

    Documentation →
  • Telegram Streaming and Long-Message Handling

    Telegram output handling was improved for long responses and structured tool activity display, with better delivery behavior and link handling for table-heavy content.

    Documentation →
  • HTTP Chat Run-Scoped Tool Panel Fixes

    HTTP UI updates resolve run-scoped debug/tool panel lifecycle issues that could previously duplicate or hide tool bubbles at turn completion.

    Documentation →

Bug Fixes

  • Telegram Long Message Regression

    A regression affecting delivery of long Telegram messages was fixed after the initial rollout.

v0.1.4

HTTP Chat Rewrite, Binary Content Guard, and Safer Runtime Defaults

GoClaw 0.1.4 delivers a major HTTP chat/transcript UI rewrite, adds binary-content guardrails across tool outputs, and improves safety/runtime behavior for shutdown phrases, unknown model context windows, and headless environments.

New Features

  • Binary Content Guardrails for Tool Results

    Tool outputs are now sanitized when binary or oversized content is detected, reducing context corruption risk from PDFs, archives, media bytes, or malformed stdout/stderr payloads.

    Documentation →
  • Parallel Tool Execution Controls

    Gateway settings now expose parallel execution controls with a safe allowlist model and max-concurrency tuning for lower-latency read/search style tool batches.

    Documentation →

Improvements

  • Web Chat and Transcript Experience Reworked

    The HTTP channel UI was extensively rewritten for better chat usability, transcript handling, and frontend architecture, with updated docs that match the new workflow.

    Documentation →
  • Safety Phrase Handling Expanded

    Panic phrase handling was tightened and shutdown phrase support was added for safer emergency control behavior across channels.

    Documentation →
  • Unknown Model Context Window Tuning

    OpenAI-compatible provider docs and setup flows now explicitly support custom `contextTokens` tuning for models not yet in the model metadata list.

    Documentation →
  • Headless Environment Fallbacks

    UI startup now detects missing display environments more reliably and falls back safely, improving server/headless deployment behavior.

    Documentation →
v0.1.4

Sandbox Presets, Session Model, and Tool/API Renames

GoClaw docs now reflect the new setup wizard security presets, updated macOS sandbox behavior, and standardized tool/config naming across memory, transcript, and provider settings.

New Features

  • Wizard Security Presets

    Setup now documents Assistant, Permissive, Hardened, and Custom security presets, including explicit acknowledgment requirements for preset-based paths.

    Documentation →
  • Expanded Setup Wizard Flow

    Onboarding now includes agent identity, optional voice settings, security selection, and a final review step for clearer first-run setup.

    Documentation →

Improvements

  • macOS Sandbox Behavior Clarified

    Sandbox docs now explain policy-managed home behavior on macOS, hidden dot-directory blocking, and clearer autodocs-read/autodocs-write expectations.

    Documentation →
  • Web Fetch Browser Fallback Options

    Web tooling docs now document browser fallback controls (`useBrowser`, `profile`, `headless`) and updated defaults for HTTP/Web UI configuration.

    Documentation →
  • User-Centric Session Key Documentation

    Channel, supervision, and concept docs now align on `primary` and `user:<id>` session keys, with explicit session IDs in supported flows.

    Documentation →

Breaking Changes

  • Provider Config Field Renamed to `driver`

    Provider examples and field references now use `driver` instead of `type`.

    Migration: Update `goclaw.json` under `llm.providers`: replace `type` with `driver` for each provider.
  • Transcript Tools Unified Under `transcript`

    `transcript_search` and `transcript_stats` are replaced by action-based usage on the `transcript` tool.

    Migration: Switch transcript tool calls to `transcript` and set `action` (for example `search` or `stats`).
  • Memory Graph Tool Names Prefixed

    Memory graph tool names are now explicit (`memory_graph_recall`, `memory_graph_query`, `memory_graph_store`, `memory_graph_update`, `memory_graph_forget`).

    Migration: Update role/tool allowlists and any tool-call references to the new `memory_graph_*` names.
  • Legacy Memory/Web Config Keys Replaced

    Legacy `memorySearch` and `tools.web.useJina` config patterns are replaced by `memory.query` and browser fallback settings.

    Migration: Move semantic search settings under `memory.query`; replace `tools.web.useJina` with `tools.web.useBrowser` and optional `profile`/`headless`.
v0.1.3

xAI Video Generation Tool Documentation

GoClaw now documents first-class `xai_video` support for text-to-video, image-to-video, and video editing workflows, including configuration, limits, and delivery behavior.

New Features

  • xAI Video Tool (`xai_video`)

    A new tool page covers Grok video generation with prompt-only creation, still-image animation, and source-video editing, plus aspect ratio, resolution, timeout, and media-delivery options.

    Documentation →

Improvements

  • Tools Index Includes Video Generation

    The tools overview now lists `xai_video` alongside other utility tools so users can discover video generation directly from the main tools page.

    Documentation →
v0.1.3

Installer Root Safety Guardrails and Sandbox Policy Clarity

The installer now adds explicit safeguards for root installs and improves PATH handling, while sandbox docs clarify expected hidden-path behavior in autodocs modes across Linux and macOS.

Improvements

  • Root Install Confirmation in Installer

    Installing as root now requires explicit confirmation, with a clear warning about security risk and a `--allow-root` override for intentional non-interactive root installs.

    Documentation →
  • Cleaner PATH Injection for Shell Profiles

    Installer PATH snippets now prepend the install directory so freshly installed binaries are found first without manual shell edits.

    Documentation →
  • Improved Installer Prompt Rendering

    TTY prompts now preserve formatted output more reliably, improving readability during interactive setup.

    Documentation →

Documentation

  • Autodocs Policy Scope Clarified

    Sandbox docs now explicitly state that autodocs hidden-path restrictions apply consistently to managed exec, managed browser launchers, and file tools.

  • Linux Hidden-Path Deny Behavior Explained

    Docs now clarify that hidden-path access denial may surface as filesystem errors in exec while file tools return policy errors, and both outcomes are expected.

v0.1.3

Installer Dependency Controls and Better Linux Setup UX

The install script now supports explicit dependency handling modes and behaves better in non-interactive environments, making Linux installs more predictable in both manual and curl-pipe flows.

Improvements

  • New Dependency Mode Flags in Installer

    The installer now supports `--deps auto|install|skip` plus `--yes` and `--no-deps` aliases so dependency installation behavior can be controlled explicitly.

    Documentation →
  • Safer Non-Interactive Dependency Prompts

    Dependency confirmation now reads from `/dev/tty` so piped installs do not consume script stdin unexpectedly, and auto-skips cleanly when no interactive terminal is available.

    Documentation →
  • Improved Linux Dependency Install Fallbacks

    Installer dependency installation now handles root/sudo detection more clearly and prints actionable manual commands when auto-install is not possible.

    Documentation →

Documentation

  • macOS Autodocs Discovery Clarification

    Sandbox docs now clarify that home-root listing can be used for discovery in macOS autodocs modes while hidden paths remain denied by policy.

v0.1.2

macOS Support & Built-in Embeddings

GoClaw now runs natively on macOS with full sandbox support. Semantic search works out of the box without requiring Ollama - a built-in embeddings provider handles it automatically.

New Features

  • macOS/Darwin Support

    Full support for macOS including sandbox-exec (Seatbelt) for secure command execution. Build from source with Homebrew GNU Make (gmake).

    Documentation →
  • Built-in Local Embeddings

    Semantic search now works without external dependencies. The hugot-local provider automatically downloads and caches the all-MiniLM-L6-v2 model on first use.

    Documentation →
  • Web-based Setup Wizard

    Configure GoClaw through a browser-based interface in addition to the terminal wizard.

Improvements

  • Sandbox Autodocs Modes

    New autodocs-read and autodocs-write modes expose common user directories (Documents, Desktop, Pictures) to sandboxed commands while keeping sensitive paths like ~/.ssh protected.

    Documentation →
  • Smarter PATH Handling

    The installer now prefers existing user-owned bin directories already on your PATH, rather than always adding ~/.goclaw/bin.

    Documentation →
  • Unified Sandbox Configuration

    Sandbox settings reorganized into sandbox.general, sandbox.bubblewrap, and sandbox.seatbelt sections for clearer platform-specific configuration.

    Documentation →

Breaking Changes

  • Cron Tool Refactored

    Cron jobs now use 'prompt' instead of 'message' and 'resultMode' (store_only, deliver, handoff_main) instead of 'sessionTarget'/'deliver'.

    Migration: Existing jobs.json files are migrated automatically with a backup to jobs.json.bak. Check logs for migration warnings.
  • LLM Provider Config

    Provider configurations now use 'driver' instead of 'type' to specify the provider backend.

    Migration: Update goclaw.json: change 'type' to 'driver' in your llm.providers entries.
v0.1.1

First Stable Release

Stability improvements and bug fixes following the initial release. This marks the first production-ready version.

Improvements

  • Stability Fixes

    Various bug fixes and stability improvements based on initial feedback.

  • Release Infrastructure

    Improved release workflow with automated builds and distribution.

v0.1.0

Initial Release

The first public release of GoClaw - a single-binary AI agent runtime written in Go. Download, configure, run.

New Features

  • Single Binary Runtime

    One static binary with everything included. No npm, no Python, no dependency hell.

    Documentation →
  • Multi-Channel Support

    Connect via Telegram, HTTP UI, or terminal TUI. Talk to your agent however you want.

    Documentation →
  • LLM Provider Support

    Anthropic Claude, OpenAI, xAI Grok, and Ollama for local inference.

    Documentation →
  • Home Assistant Integration

    Native integration to control lights, query sensors, and subscribe to events.

    Documentation →
  • Browser Automation

    Built-in Chromium for web scraping, screenshots, and automation.

    Documentation →
  • Self-Update Mechanism

    GoClaw can update itself with checksum verification.

  • User Authentication

    Owner and user roles with separate permissions. Guest authentication for unknown users.

    Documentation →
  • Distribution Packages

    Available as Debian packages (.deb) and Docker images on GHCR.

    Documentation →