v0.16

What's Changed

• Rebrand MPA to humux by @mattmezza in #140
• www: initial marketing site for humux (Human Multiplexer) by @mattmezza in #141
• refactor: monorepo structure by @mattmezza in #142

Full Changelog: v0.15...v0.16

v0.15

What's Changed

• Per-persona email & calendar accounts with delegated access (#110) by @mattmezza in #113
• GitHub App integration: bot identity, fine-grained permissions, per-persona scoping (#111) by @mattmezza in #112
• Contacts (CardDAV) accounts + default-agent account bindings (#110 follow-up) by @mattmezza in #117
• Per-persona GitHub Apps + explicit PAT/App selection (#111 follow-up) by @mattmezza in #118
• fix(email): correct himalaya v1.2.0 syntax + gate every command segment by @mattmezza in #119
• feat(#116): show context token count + % of window in Inspect tab by @mattmezza in #120
• feat(#114): split LLM settings tab into SysPrompt / Inference / Providers by @mattmezza in #121
• Merge Assistant + Personae into one Agents tab; kill 'persona' (#115) by @mattmezza in #123
• docs: kill leftover 'per-persona' in Tools section (post-#115) by @mattmezza in #125
• feat(#124): Jobs table — agent filter, hardened to survive re-renders by @mattmezza in #126
• Add OpenRouter as a full LLM provider (#128) by @mattmezza in #130
• fix: serialize concurrent turns of one chat with a per-chat lock by @mattmezza in #132
• feat(#129): per-agent per-chat Telegram trigger/DM settings by @mattmezza in #131
• Agents by flags: default + enabled kill-switch (drop active_agent) by @mattmezza in #127
• Remove Channels tab — each agent is its own Telegram bot (#133) by @mattmezza in #134
• feat(#135): restructure agent editor into tabs by @mattmezza in #136
• feat: Voice tab + agent-card relabel (emoji out, name/role·slug) by @mattmezza in #139

Full Changelog: v0.14...v0.15

v0.14

What's Changed

• feat: allow editing persona slug (#69) by @mattmezza in #72
• feat(jobs): hide completed jobs from main list behind a 'Show completed' toggle by @mattmezza in #73
• fix(scheduler): run scheduled jobs in the originating agent/chat (#71) by @mattmezza in #74
• fix(llm): config-driven max_tokens + truncation detection (#77) by @mattmezza in #85
• feat(logs): multi-agent log streams in the Logs tab (#75) by @mattmezza in #83
• feat: coding harness — confined file read/write/edit/list/grep/run tools (#76) by @mattmezza in #86
• fix(agent): tool-exec resilience — guard params, catch errors, break repeat-failure loops (#78) by @mattmezza in #87
• fix(permissions): close catch-all ALWAYS rule + fail-open approval (#79) by @mattmezza in #88
• fix(telegram): chunk long messages + cap command in approval text (#80) by @mattmezza in #89
• feat(artifacts): reuse coding-harness file tools instead of a separate artifact mechanism (#82) by @mattmezza in #91
• feat(telegram): emoji reactions via set_reaction tool (#70) by @mattmezza in #92
• feat(voice): add Kokoro 82M offline TTS backend (#84) by @mattmezza in #90
• fix(voice): condition TTS on the reply language (#95) by @mattmezza in #96
• feat: per-persona tool identities (own gh token + browser profile) (#93) by @mattmezza in #94
• fix(personae): renaming/deleting a starter persona no longer duplicates or resurrects it (#102) by @mattmezza in #103
• feat: convert WhatsApp from channel to tool (#97) by @mattmezza in #105
• feat(jobs): scope jobs per persona — show + filter in UI (#101) by @mattmezza in #106
• Remove personalia field — merge into character & tone (#98) by @mattmezza in #107
• Replace Chats tab with developer Inspect tab (last-sent LLM payload per context) (#99) by @mattmezza in #104
• feat: scope permissions per agent/persona (#100) by @mattmezza in #108
• Improve agent context quality and add structured memory write by @mattmezza in #109

Full Changelog: v0.13...v0.14

v0.13

What's Changed

• fix: per-action write state so one write failure doesn't block the rest by @mattmezza in #20
• Thinking-level support across all inference kinds (LLM tab) by @mattmezza in #21
• feat(voice): clean non-pronounceable chars from TTS replies by @mattmezza in #22
• fix(jobs): block create only on live duplicate id (#11) by @mattmezza in #24
• feat: deepseek-v4-flash default + terminal REPL by @mattmezza in #23
• feat(agent): batch write-action approvals into one prompt (#12) by @mattmezza in #25
• feat: persona profiles — swappable agent identities (#13) by @mattmezza in #27
• feat: vision fallback — caption images via a secondary model on non-vision models by @mattmezza in #26
• feat: optional headless browser automation (#16) by @mattmezza in #28
• Secrets vault: encrypted two-vault backend with per-persona access (#19) by @mattmezza in #31
• Per-chat persona binding + isolated contexts (channel-agnostic) (#14) by @mattmezza in #32
• Show CoT thinking trace in admin UI log tab (#33) by @mattmezza in #38
• feat(secrets): migrate static credentials onto the infra vault + collapse redundant UI (#35) by @mattmezza in #40
• feat(artifacts): agent-crafted web pages served at /artifacts/ by @mattmezza in #37
• feat: bot-per-persona — each persona as its own Telegram bot (#29) by @mattmezza in #39
• feat(memory): two-tier scoped memory — shared pool + per-persona private (#42) by @mattmezza in #45
• fix(agent): inject memory + reflections per-turn, not in frozen snapshot (#41) by @mattmezza in #43
• feat(memory): recall_memory tool — deliberate full-store semantic lookup (#47) by @mattmezza in #49
• fix(agent): inject skills index per-turn, not in the frozen snapshot (#46) by @mattmezza in #48
• feat: subagents — on-demand + scheduled spawning with lifecycle management (#15) by @mattmezza in #44
• feat(skills): serve the index on-demand via search_skills/list_skills (#50) by @mattmezza in #52
• Fix Telegram formatting: avoid tables, use code blocks for commands by @mattmezza in #54
• feat: reply-decision gate to stop infinite loops in group chats (#36) by @mattmezza in #53
• fix(telegram): typing/thinking indicator on Telegram Web (K) (#57) by @mattmezza in #58
• feat(vault): enable secret removal from vaults (#56) by @mattmezza in #60
• feat: image generation tool (OpenRouter, fal.ai, OpenAI) with admin UI + wizard (#55) by @mattmezza in #61
• feat(telegram): group multi-agent rooms — turn-taking + loop guard + speaker tags (#30) by @mattmezza in #59
• Auto-dismiss permission approval messages after user interaction by @mattmezza in #63
• feat(voice): advertise voice reply as a base capability by @mattmezza in #66
• Scoped /yolo mode + close the permission-generalisation bypass by @mattmezza in #67

Full Changelog: v0.12...v0.13

v0.12

What's Changed

• Tools tab (gh) + prompt caching + conversation compaction by @mattmezza in #4
• Re-vendor wacli to upstream openclaw/wacli v0.11.0 by @mattmezza in #6
• feat(memory): unified update pipeline + embeddings + forgetting + hygiene (closes #5) by @mattmezza in #7

Full Changelog: v0.11...v0.12

v0.11

Full Changelog: v0.10...v0.11

v0.10

Full Changelog: v0.9...v0.10

v0.9

What's Changed

• feat: expose and control system prompt from admin UI by @mattmezza in #1

New Contributors

• @mattmezza made their first contribution in #1

Full Changelog: v0.8...v0.9

v0.8

Full Changelog: v0.7...v0.8

v0.7

Full Changelog: v0.6...v0.7