8.2 Software changelog

This page records the main user-facing changes in Teloa by version number. The current stable release, 0.2.0, is available on GitHub Releases and Docker Hub, while npm still provides 0.2.0-alpha.7. Historical entries retain their actual release status. For how to run Teloa today, see Install and run Teloa.

0.2.0 (stable · GitHub Release / Docker Hub)

2026-10-18 · The stable Community release. Its native package is available on GitHub Releases for the macOS ARM64 platform verified in this release; Docker Hub provides the matching Linux ARM64 image. npm still provides 0.2.0-alpha.7; publishing the stable npm package requires the publisher to sign in. Check the release attachments, checksums and actual channel version when installing.

Upgrading from Alpha.7: capabilities and key changes

These entries describe current capabilities and improvements, not features that are all new. See projects, knowledge and models for setup and boundaries.

• Projects that keep working context. Alongside linked tasks, employees, groups, automations, materials and deliverables, projects now have dedicated conversations and usable project context. The project goal, brief, active rules, required materials and relevant memories can accompany the next model request. Inspect what was used and its sources, review memory candidates, choose a new conversation without long-term memory, and explicitly opt into personal preferences. Memory sharing uses a fixed revision and can be withdrawn.
• Knowledge and local document retrieval. Track explicitly selected local Markdown files, maintain their versions, add them to an index and inspect cited excerpts. Prepare Qwen3 Embedding 0.6B or EmbeddingGemma 2 with confirmation instead of silently downloading model files. Indexing runs on the Teloa deployment device; retrieved excerpts may be sent to the chat model you choose. This is not automatic scanning of the computer or indexing of every previewable file format.
• Local and remote model choices. Bring your own provider credentials, choose a conversation model and configure employees separately. Manage supported local chat models through Ollama: inspect the runtime, confirm downloads, follow or cancel preparation, and connect an existing model. A local embedding model and a local chat model serve different purposes; enabling one does not switch the other.
• AI employees, teams and apps. Market entries distinguish AI employees and AI teams. A team can supply employees, skills, reference materials, connections and work templates. Adding an employee continues the shared setup instead of leaving an unfinished duplicate. Apps manage installed capabilities and connections; adding a template does not silently change models, grant permissions or start work.
• A clearer conversation and group experience. Conversations, employees and groups have separate lists and personal organization. Replies to a group-stream message stay in the stream with a link back to that message; replies inside a topic stay in the topic. Explicit @ mentions carry through to the assigned work. Cross-business collaboration still checks the employee's business and tool permissions.
• Natural-language work, with versioned results. Describe a task in Markdown and carry its source conversation or business context into the draft. Follow the actual execution, handle approvals, stop work, preview or download deliverables, and send feedback or a selected passage back for revision. Earlier versions remain readable; a business acceptance continues to refer to the accepted version. Saving a task does not itself execute it. Some employee and group creation flows still use structured steps.
• Reusable methods and memory. Save an accepted way of working as a skill or a plan. A newly saved plan stays paused until enabled. Auto Dream produces private daily summaries and can save sourced employee experience for later work, with sources and withdrawal controls. Your twin is distinct from an employee: habit observations are private samples and do not automatically become the context of ordinary conversations or train model weights.
• Business work connected to records and dashboards. Describe a business configuration in natural language, review its draft, import records, connect approved sources and follow work through to an accepted result. Records and Dashboards now show their own pages and remember their own selection. Dashboard cards remove repeated titles and shared explanations, fit their content, and show chart categories and values; missing data is still distinguished from zero.
• Voice and the companion assistant. Use local SenseVoice transcription, voice messages and calls with an employee or the companion. Speech playback supports MiniMax, OpenAI and ElevenLabs, with continuous playback; MiniMax provides Chinese/English voice lists and preview. Keep call controls available while navigating; ending a call does not stop the original work. The companion can be hidden or restored without stopping its conversation.
• Execution tools and real file delivery. Use temporary task teams and Workflow, PTC or explicitly requested Ralph execution within their approval boundaries. External Codex and Claude Agent integrations use credentials you configure. Open Markdown, code, images, PDF, HTML, Office files and tables in the workbench preview, and retain a specific file version as a deliverable. Browser/Computer Use remain optional, disabled until configured and authorized; IM channels and connections need their own setup.
• Continuity and everyday usability. Compact detail drawers, fewer repeated explanations, current Apps/Employees navigation labels, corrected English counts and buttons, separate drafts and clearer pending/failure states reduce unnecessary steps. Upgrade commands preserve the installation identity and data and create a backup before switching. The runtime is pinned to DSH 0.2.1-rc.2.

Installation, upgrades and support

• Use the stable command package to run teloa stop, teloa upgrade --to 0.2.0 and teloa status. Keep the original --home for a custom installation; the upgrade retains identity and data and creates a backup before switching. Keep an existing Docker deployment's Compose project and data volumes, and back it up before updating the image.
• Native macOS ARM64 and Docker Linux ARM64 are verified separately; amd64 and other native operating systems are outside this release's acceptance. Configure and check each model, speech provider and optional device combination according to its guide. A stable version number does not grant permissions or guarantee result quality.
• See installation and backup and upgrades. Stable documentation is preserved under /v/0.2.0/; the root path continues to track current documentation.

0.2.0-beta.7 (preview · GitHub Release / Docker Hub)

2026-10-18 · The native package is published on GitHub Releases and has been verified on macOS arm64 with Node.js 24. The Docker image has passed an isolated startup check on Linux ARM64. npm still provides 0.2.0-alpha.7. It includes everything in 0.2.0-beta.6.

This historical version collected Beta-stage business, marketplace and installation fixes. The complete capability overview for stable 0.2.0 is in the section above.

Latest fixes

• Fix: business pages now separate Records from Dashboards, and each tab remembers its own page. Dashboard cards show their title once, state shared notes once per page (cards still note their own missing or truncated data), size to their content, and label chart bars with categories and values. Pages created from an official template show their built-in page names in the interface language, while names you changed stay as you set them.
• Fix: in the marketplace, a team's skills and connections are counted separately, a team added to this computer shows Added with Continue adding, counts use the singular form for one item, buttons no longer wrap their labels in English, and the template import dialog wording was corrected.
• Upgrades: run teloa upgrade --to 0.2.0-beta.7 from the new command package to upgrade an existing installation, such as 0.2.0-beta.6, 0.2.0-beta.5 or 0.2.0-alpha.7, while keeping its identity and data.

Known limitations are the same as in 0.2.0-beta.4.

0.2.0-beta.6 (preview · superseded by 0.2.0-beta.7)

2026-10-18 · The native package is published on GitHub Releases and has been verified on macOS arm64 with Node.js 24. It is not published to npm or Docker Hub. It includes everything in 0.2.0-beta.5.

• Fix: in-app guidance now points to the places that exist today: resume a newly added employee from Employees, open files and skills from Apps, reopen a configuration draft from Added, and the Auto Dream notice opens the employee it refers to. Wording that still said solution now says template, and several English labels in the work results panel and import forms were corrected.
• Upgrades: run teloa upgrade --to 0.2.0-beta.6 from the new command package to upgrade an existing installation, such as 0.2.0-beta.5, 0.2.0-beta.4 or 0.2.0-alpha.7, while keeping its identity and data.

Known limitations are the same as in 0.2.0-beta.4.

0.2.0-beta.5 (preview · superseded by 0.2.0-beta.6)

2026-10-18 · The native package is published on GitHub Releases and has been verified on macOS arm64 with Node.js 24. It is not published to npm or Docker Hub. It includes everything in 0.2.0-beta.4.

• Fix: when another add of the same catalog employee is still installing its methods, adding that employee no longer returns early as pending; it continues to the same method installation and returns the complete receipt for the same employee.
• Upgrades: run teloa upgrade --to 0.2.0-beta.5 from the new command package to upgrade an existing installation, such as 0.2.0-beta.4, 0.2.0-beta.3 or 0.2.0-alpha.7, while keeping its identity and data.

Known limitations are the same as in 0.2.0-beta.4.

0.2.0-beta.4 (preview · superseded by 0.2.0-beta.5)

2026-10-18 · The native package is published on GitHub Releases and has been verified on macOS arm64 with Node.js 24. It is not published to npm or Docker Hub. It includes everything in 0.2.0-beta.3.

• Fix: running a plan right away while the scheduler is recovering the same run no longer reports a conflict, marks the plan as failing or leaves an extra session; the run starts once.
• Upgrades: run teloa upgrade --to 0.2.0-beta.4 from the new command package to upgrade an existing installation, such as 0.2.0-beta.3 or 0.2.0-alpha.7, while keeping its identity and data.

Known limitations: saving a confirmed deliverable's method as a plan from the conversation, running it once manually, opening the result and completing the task have been verified with a real model; a run started by the calendar schedule itself has not. Other limitations are the same as in 0.2.0-beta.3.

0.2.0-beta.3 (preview · superseded by 0.2.0-beta.4)

2026-10-18 · The native package is published on GitHub Releases and has been verified on macOS arm64 with Node.js 24. It is not published to npm or Docker Hub. See Install and run Teloa for installation and upgrades.

• Runtime: DSH is pinned to 0.2.1-rc.2.
• Upgrades: run teloa upgrade --to 0.2.0-beta.3 from the new command package to upgrade an existing installation, such as 0.2.0-alpha.7, while keeping its identity and data. Other versions still upgrade from the npm registry.
• Work and deliverables: assign work to the general agent or an AI employee and follow it in the original conversation. Deliverables keep versions; give feedback or revise a selected part, and earlier versions stay readable.
• Reusable methods: save a confirmed way of working as a skill, or as a plan that stays paused until you enable it.
• Collaboration: group conversations carry explicit @ mentions through the work; employee chats are kept separate from general conversations.
• External coding agents: run Codex or Claude Agent tasks from the workbench with native approvals, using credentials you configure.
• Web search and fetch: optional DeepSeek search and page fetch in Settings > Connections and runtime > Web search, with your own credentials.
• Market: one flow to create employees and teams; installing an employee brings its complete resources; reviewed app packs; share an AI employee as a template.
• Business: local business work with approved record changes, and dashboards that reflect task results.
• Voice: local speech recognition, and speech playback with MiniMax, OpenAI or ElevenLabs, including compact bilingual voice selection, preview and continuous playback.

Known limitations: saving a confirmed deliverable's method as a plan through the conversation, enabling it and its first scheduled run have not been verified end-to-end with a real model. In complex analyses, model conclusions can claim more than the evidence supports; review deliverables before relying on them. Claude Agent with Anthropic models through your own account sign-in has not been verified.

0.2.0-beta.2 (preview · superseded by 0.2.0-beta.3)

2026-10-18 · The first public 0.2.0 Beta preview. Its GitHub Release is unchanged. Its command package cannot upgrade an existing installation to its own version; use 0.2.0-beta.3 instead.

0.2.0-alpha.7 (published · Alpha)

2026-10-01 · The exact version is published on npm as @teloa/cli and Docker Hub as teloa/teloa. The current documentation covers this version. Docker has been verified on Linux ARM64; amd64 has not been verified.

• Build and verify an SOC business from the business page: connect a read-only alert source, declare its mapping and enable sync, assign a real Task/Run from a record, then see its progress and the exact version of the accepted deliverable on the same business page. Other industries are examples without end-to-end acceptance.
• CSV and XLSX imports preview data, write a fixed batch, and recover the same request after a lost response or restart. Sync rules are controlled per mapping; equal external IDs from different sources do not overwrite local records.
• Includes projects, task teams, updated extension management and composer improvements, along with marketplace, connection, local-model and extension work. External connections and extensions still need configuration and authorization.