→00VSCode Extension · Marketplace
The memory secretary
for your project.
viway watches your AI agent’s dialogue and, after every reply, extracts decisions, facts and open questions into a living knowledge base on its own. No manual work. Context is never lost — not even after /compact, a restart or a folder move.
→How the processes flow
Every subsystem is a clear flow you launch from the dialogue and watch in the dashboard.
The agent replies → auto-trigger → the secretary reads the turn → structured operations on .viway/ → a living wiki of 8 sections. Zero manual work on your side.
Mission brief → the architect (O) designs, the implementer (D) builds on its own branch → confirmations and clarifications from the dialogue → review → result. Two agents under your control.
A task to verify → approval or autostart → Gemini walks through it step by step in a real browser → a JSON report → the dashboard, and optionally into a Marathon as evidence. A stuck run can be stopped with one button.
Marathon start → the agent pulls the next step plus a reality-check → does it → reports → the secretary reconciles with the project and amends the plan. Progress is visible in the dashboard in real time.
A prompt from the task → approval → Codex ($imagegen / gpt-image) → a ready file to staging, into the project on request. Billed to your Codex; viway never spends an API key.
A question from the dialogue → query / recall / semantic → the secretary searches .viway/ → a precise answer with citations. The memory answers right in the chat.
→01Key features
The secretary — a separate agent — maintains the knowledge base on its own after every reply: it classifies the turn, decides what matters and updates the right wiki section. Zero manual work — you just work.
/compact, a VSCode restart, a folder move — your project context stays put and is never lost.
viway gathers dialogue from every source: Claude, Codex, Copilot, Kilo, Cline, Gemini and Antigravity — running in parallel — share one common knowledge base and never duplicate work that’s already done.
Four providers to choose from. One key — and you decide which model runs your memory.
The “command HQ” runs a mission with two agents — an architect (O) and an implementer (D) — on separate branches, with confirmations and clarifications straight from the dialogue.
The agent queries the memory straight from the dialogue — “what did we decide about X?”, “have we seen this before?” — via query, recall and semantic search, and gets a precise answer with citations from the wiki.
A real-time turn feed, colour-coded statuses, project metrics and a cost audit — all on one screen.
Fonts are bundled, with no external CDN dependencies. The interface opens even with no network.
query · recall · catchup · note · mission-brief · marathon · coordinator · playbook · imagegen — ready-made skills install with one click.
A browser QA agent: viway spins up the Gemini CLI with a browser MCP; it opens your app, clicks and checks on its own — and returns a structured report: verdict, steps, findings, console errors.
A living plan under the secretary’s watch: the agent authors the steps, the secretary reconciles them with the project’s reality and amends the plan. The plan survives context compaction and session changes.
Icons, covers, mockups straight from the task — via your Codex ($imagegen / gpt-image). To staging by default; into the project only on explicit request.
Semantic search via embeddings finds what you need even when the words don’t match. And recall pulls ready solutions to past problems — the symptom → cause → fix triple.
Project playbooks: turn a working procedure into a skill the agent finds and runs on its own — with an optional enforcement gate for critical steps.
Before every run viway snapshots the knowledge base — roll any result back with one pick from the list.
A one-click reviser cross-checks the knowledge base against the real code + git: it finds closed-but-still-open questions, stale references, stack conflicts (wiki says Tauri while the code is Electron) and broken links in docs. Report-only — you apply the findings yourself, in bulk or one by one.
→02How it works
The secretary fires on its own after every agent reply. You just work — the knowledge base fills up in the background.
You work with Claude Code, Codex CLI or Antigravity as usual.
Every agent reply launches the secretary — no buttons, no commands.
The model analyses the dialogue and picks out what’s worth remembering.
Decisions, facts and questions become tidy records.
Everything lands in a structured knowledge base right inside the project.
→03Problem & solution
An AI agent is brilliant in the moment but forgetful over time. Every /compact, restart or new session wipes what you’d already decided. viway turns the stream of dialogue into durable project memory.
/compact and restarts→04Knowledge base
Project memory is organised like a personal archive — each section owns its own layer of knowledge. Tidy, readable, under control.
→05Multi-provider
Connect any of four providers. Switch the model to fit the task and budget — viway stays the same.
A single access point to dozens of models through one key.
Direct access to the Claude model family.
Qwen models via Alibaba Cloud.
The Gemini family for a flexible balance of price and quality.
→06More power under the hood
Command HQ
The orchestrator splits the roles: one agent designs, the other implements. You confirm every step — no improvisation, full transparency into the work.
Communicator
→07Savings
Request caching cuts repeat costs — up to ~75% savings. Memory works in the background and won’t break the bank.
The secretary reuses already-processed context instead of paying for it again. The longer a project lives, the bigger the savings.
→08Privacy & control
The knowledge base lives right inside the project. Before every write — an auto-snapshot, one-click rollback. And crucially: viway never touches your project code.
Memory is stored locally in the project folder. No cloud storage — your data stays with you.
An auto-snapshot before every write. Something off? One-click rollback restores the previous state.
The extension works only with its own knowledge base. Your source code stays untouched.
→09See it in action
On the left — settings and provider selection; on the right — a live turn feed with colour-coded statuses and metrics. Everything the project remembers, right in front of you.
→10Install
Find viway in the VSCode Marketplace or install it by the id viway.viway-v3. One button — and the extension is in your editor.
Pick one of the four providers and paste your key. OpenRouter is an easy start: one key unlocks dozens of models.
Activate the built-in skills query · recall · catchup · note · mission-brief — and the agent can talk to the project memory directly.
From there viway does everything itself. After every agent reply the secretary updates the living knowledge base — and you watch it on the dashboard in real time.
viway 0.52.0 is already on the VSCode Marketplace. Install it in a minute — and stop losing context.
→12Contacts
A question, idea, bug or suggestion — drop me a line. I answer personally.