Axiom V1.6

A major pass focused on letting Axiom run against your own hardware, plus hardening the systems that keep long conversations and multi-agent runs coherent.

Bring your own inference server — point Axiom at any self-hosted OpenAI-compatible endpoint (e.g. your own Ollama box) as a first-class model option, in both Normal Chat and the Workplace Council. A new Hybrid Local mode blends local reasoning with your self-hosted backend, with tool-calling and context-window budgeting that correctly scale down for smaller self-hosted models instead of assuming a large cloud context window.

Context compaction, fixed for real — the automatic long-conversation summarization system (Normal Chat and Workplace Council) had a bug where summaries could silently vanish instead of actually being used going forward. Both are now correct, with safer fallback behavior and clearer logging when something needs attention.

MCP connectors & cloud agentic tools — Gmail/Drive, GitHub, and Todoist OAuth connectors, a new Settings Connectors UI, and Workplace GitHub integration.

Security — the OpenRouter API key is now encrypted at rest via Windows DPAPI.

Reliability & polish — exact (not estimated) OpenRouter token usage, diff-aware artifact Critic reviews, a first-run default model downloader, native markdown rendering in Workplace cards, background council run completion notifications, chat search/rename/pinning, bounded rendering for long chats, Builder vision support in Workplace, a Settings backend log viewer, transient chat failures now surface in a banner instead of failing silently, and a new pure-logic unit test suite.

Runs local-first on Windows. Unzip and run, or update in-app.

Axiom V1.5

Axiom V1.5 — Reliability & Intelligence Release

The biggest engineering pass since launch: 34 commits and thousands of lines changed across 50+ files (May–July), focused on making every part of Axiom dependable enough for daily use.

Cloud chat can no longer hang — streamed responses have real deadlines, mid-stream provider failures are detected, and Axiom automatically falls back to a working model instead of freezing.
Local models got smarter, at every size — models are profiled into size classes (<1B to 10B+) with tool routing, context budgets, and prompts scaled to what each can actually handle. A new intent router, semantic tool-call validation, and a per-model reliability ledger mean small local models now use tools correctly instead of hallucinating them.
Codebase Access you can trust — council patches are verified to actually implement your request, edits use fuzzy anchor matching with exact-byte retries, applying patches no longer litters your repo, and Undo always works.
Production hardening — single-instance protection, friendly crash reporting with diagnostic logs, log rotation, encrypted API-key storage, and full CPU fallback on non-NVIDIA machines.
Runs local-first on Windows. Update in-app or grab the installer below.

Axiom V1.4

I fixed the screen resolution issue so the UI now adapts properly to different monitor sizes and DPI settings — the window fits itself to your screen on startup and the sidebar, padding, and panels resize smartly depending on whether you're on a compact, standard, or wide display.

I also made some solid improvements to the Council/Workplace chat for both local and cloud modes. Each task now gets a clear internal "contract" (goal, requirements, constraints, acceptance checks) that the Architect, Builder, and Critic all work from, so the Critic can actually verify the Builder's work against concrete checks instead of just trusting its description. On the cloud side, I tuned token budgeting per role so things stay efficient and compatible across different models and bumped up how much document content cloud mode can handle.
Additionally, the 'Project Canvas' can be manually used with this command in the textbox '@ ProjectCanvas' (case insensitive), - put the @ and the ProjectCanvas text together). Furthermore, alot more optimizations and improvements done to the local LLM inference for smaller LLMs.

Lastly, I rewrote the README to actually match the real code — fixed some wrong model names and sandbox claims (it only supports Python and Java, not JS/PowerShell/C#), corrected the local model and library names, and added proper docs for the AI tools, memory system, and supported file types.

Happy Building!

Axiom V1.2

This is a major overhaul and the first official version of Axiom.

V1.2 brings improvements to the council backend/pipeline and role fixes.
Web search fixes & improvements
NEW cloud models
GPU usage improvement (Nvidia)
context improvements and MUCH more.

New feature: Artifact Rendering

AXIOM - Release v0.01

Pre-release version of Axiom

Remember: This is a PRELEASE version, bugs and glitches could appear, my testing is from MY experience, i am releasing to gather reviews, suggestions, and actual usage from users.