AI Native Lang
What's newv0.8.0

ArmaraOS v0.8.0 — missions, session goals, and a sharper first run.

This drop ships graph-native Missions with progress stats and shareable recaps, lightweight session goals for multi-step continuity, Ollama Cloud and OpenCode Go providers, desktop AINL bootstrap on first launch, and a polished Get started onboarding flow — still with credentials Vault, honest AINL MCP errors, self-learning proposals, premium agents, swarms, and up to ~70% token savings on recurring workflows.

Download v0.8.0All installers on GitHub
Missions & continuity

Multi-step objectives that stick around

Graph-native missions with progress you can share — plus lightweight session goals even before you flip on the full mission substrate.

Graph-native MissionsFeature DAGs, worker dispatch, handoffs, assertions, stall recovery, and auto-remediation — dashboard, CLI, and REST API.
Progress, stats & share recapOutcome % and optional effort % from tool budgets; career badges and a Share recap PNG export for social proof.
Session goals (Codex-style)Durable multi-step objectives upsert SessionGoal graph nodes and a GOAL telemetry chip — promotion to a full mission still needs your OK.
Post-tool capability cooldownAfter tools run, follow-ups like “why did you stop?” keep capabilities advertised without re-triggering conversation suppression.
Providers & desktop

More models, AINL ready on first launch

New provider paths and a desktop that bootstraps embedded AINL before the daemon starts.

Ollama Cloud + local/cloud scopingSubscriber API at ollama.com with OLLAMA_API_KEY; local Ollama stays scoped separately from cloud credentials.
OpenCode Go driverOpenAI-compatible and Anthropic Messages paths for MiniMax and related models via OpenCode Go.
Desktop AINL prelaunch bootstrapEmbedded AINL venv is installed/repaired before daemon boot — scheduled cron and MCP work out of the box.
First-run onboarding glowFresh-install Get started session, hardened Telegram setup wizard, and Operator terminal excerpt fallback.
Look & feel

Redesigned, easier to read, easier to talk to

A fresh dashboard for everyday use, with on-device voice when you'd rather just talk.

All-new UI/UXPolished light + dark themes across every page, with consistent design tokens.
Talk to Armara, Armara talks backBuilt-in speech-to-text and text-to-speech run on your machine — no cloud mic by default.
Agents that do real work

Premium Hands, swarms, and 40+ ways to reach them

Pre-built autonomous agents you activate with one click — and they reach you on the apps you already use.

9 token-gated premium agentsAutomated browsing, deep research, predictions, video clipping, lead generation, social media, trading and more.
Multi-agent + sub-agent swarms (beta)Agents can spawn helper agents and coordinate — every step is shown in inspectable orchestration traces.
40+ channel connectorsTalk to your agents from your phone over Telegram, WhatsApp, Discord, Slack, Signal, Email, and more.
AINL tooling that tells the truthInvalid graphs and missing MCP adapters surface as real tool errors with repair guidance — so agents fix AINL instead of pretending a bad run succeeded.
A brain that learns

It gets sharper every time you use it

ArmaraOS quietly learns what works, what fails, and what you prefer — without sending anything to the cloud.

Graph Memory + Auto Persona EvolutionLearns your preferences from real usage signals — no questionnaires, no extra LLM calls.
Pattern Memory + PromotionRemembers successful workflows and promotes them into reusable patterns automatically.
Auto improvement proposalsWhen a workflow repeats and proves itself, ArmaraOS can stage validated pattern and procedure proposals for you to review — less manual housekeeping.
Trajectory CaptureFull execution traces of every run, available for replay and review in the dashboard.
Failure LearningRemembers and prevents repeated errors so you don't hit the same wall twice.
Smart SuggestionsContext-aware recommendations grounded in the agent's own history.
Closed-Loop ValidationImprovement proposals are validated before they're adopted — nothing changes silently.
Smart DetectionSpots recurring tasks and offers to turn them into AINL workflows with MCP tools, validation, and auto-correction.
Cost & control

Cheaper to run, easier to trust

See exactly what your agents are costing you — and cut that bill without losing context.

Settings → VaultA credentials center for API keys and secrets: catalog dependencies, test what applies, and keep an audit-friendly record of changes.
Adaptive CompressionLearns the right amount to compress per project — up to ~70% token / API cost savings on recurring workflows.
Visual Analytics, Monitoring & Audit LogsDashboards for token / API spend, budget limits, system health, and a tamper-evident audit trail.

Free & open source · Apache 2.0 · Powered by AI Native Lang