// PERSISTENT MEMORY FOR CODING AGENTS

A Wiki for Your Coding Agents

AGENTS.md for your whole org, with a human-readable audit trail and agent tooling on top. Stop losing institutional knowledge between sessions.

./LEARN_MORE
~/my-project
vibe skill code-review
→ Always use lib/logger.ts for structured logging
→ voice-tools uses WebSocket streams — check cleanup
→ Error responses must include request_id
vibe write "Use lib/logger.ts for all logging"
✓ Written to org/conventions/logging.md
✓ Skill code-review updated automatically

THE PROBLEM

Coding agents are stateless. Every session starts fresh. When an agent discovers that your team has a shared logging library, fixes the issue, and moves on — that knowledge dies.

Documentation icon

AGENTS.md / agent.md

Single-project scope. No cross-project knowledge. Manually maintained by humans.

LIMITED SCOPE
Books icon

Confluence / Notion

Built for humans, not queryable by agents. Knowledge exists but agents can't reach it.

WRONG AUDIENCE
Search icon

RAG Over Codebase

Finds what is — not what should be. Can't capture conventions, decisions, or lessons learned.

WRONG DATA

THE SOLUTION

vibedecoding.io is a persistent organizational memory layer for coding agents — a wiki that agents can read from and write to, continuously enriched by both humans and automated agents.

LAYER 1

The Human Layer

  • Markdown wiki, navigable via a web portal
  • Humans browse, edit, and review like any wiki
  • Plain markdown is the canonical source of truth
event sourcing
LAYER 2

The Agent Layer

  • Structured, indexed representation optimized for agent queries
  • Rebuilt automatically whenever the wiki changes — on write, on push
  • No manual compile step; index maintenance is invisible to users
  • No magic black box — the source is always auditable
vibedecoding-wiki/
├─ org/
│ ├─ conventions/
│ │ ├─ logging.md
│ │ └─ error-handling.md
│ ├─ decisions/
│ └─ skills/
│ ├─ code-review.md
│ └─ onboarding.md
├─ projects/
│ └─ voice-tools/
│ └─ skills/
│ └─ code-review.md
├─ users/
│ └─ ian/
│ └─ skills/
└─ .vibe/
├─ config.yaml
└─ agents.yaml

Git-Backed Storage

The wiki is a git repository. Full provenance for free — every fact has an author and timestamp. PR-based review flow for agent-proposed changes. Familiar editing workflow for humans.

AGENTS.md vs VIBEDECODING

They complement each other. vibedecoding can inject a relevant summary into AGENTS.md at project init.

AGENTS.md / agent.md vibedecoding
Scope Single project Org, project, and user layers
Author Human, manually Human + agent-assisted
Location In the repo External, centralized
Lifespan Lives with the repo Persistent, independent
Example "Run tests with npm test" "Always use lib/logger.ts for structured logging"

THE CLI

The primary interface for agents and humans alike. Works with Claude Code, Cursor, Aider — any agent framework. No API integrations to maintain.

Skill
vibe skill code-review

Get a named skill — org, project, and user layers merged into one tailored output. No keywords required.

Query Ad-Hoc
vibe query "logging patterns"

Ad-hoc query when no skill exists yet. Get org-wide conventions relevant to your task.

Write
vibe write "Use @lib/logger.ts for logging"

Write a discovered convention back to the wiki. Indexing happens automatically.

Skill Create
vibe skill create code-review

Create a named skill. The system populates and maintains it across all layers as the wiki grows.

Agent Bootstrap

The only integration required — add this to your agent.md:

agent.md
## Organizational Knowledge
This project uses vibedecoding for institutional knowledge.
- Before a code review, run `vibe skill code-review`
- Before writing code on a new topic, run `vibe query <topic>`
- When you discover a reusable pattern, run `vibe write`
- Run `vibe --help` for full usage

SKILLS

Skills are the primary interface between the wiki and agents. A skill is a named, layered, living context bundle — everything an agent needs for a specific task, assembled from multiple scopes.

~/voice-tools
vibe skill code-review # everything relevant to reviewing code
vibe skill onboarding # everything a new team member needs
vibe skill architecture # system design decisions and constraints

Layered Scopes

Skills are composed from three layers, merged in order. When an agent calls vibe skill code-review --project voice-tools --user ian, it gets all three layers merged into one coherent output.

ORG "always check for structured logging"
PROJECT "voice-tools uses WebSocket streams — check cleanup"
USER "I care especially about error boundaries"

Layers annotate rather than override. Both facts surface with context — the agent reasons about the tension.

DECLARED

You Name the Intent

Create a skill and the system populates and maintains it across all layers as the wiki grows. New facts are automatically routed to relevant skills.

DISCOVERED

The System Surfaces Patterns

Written 8 facts about auth across 3 projects? The system suggests an auth skill. Accept, reject, or rename — then it's maintained going forward.

AGENTS

There are three types of agents. Each has a distinct job.

YOU OWN

The prompts, configuration, and trigger rules. Define what agents do and when they run.

WE PROVIDE

Agent code, VM runtime, tool integrations, and execution guarantees. Reliable, isolated execution.

Event Sources → Agents → Wiki

GitHub release Release Summarizer org/releases/
Linear milestone Milestone Summarizer projects/{ name }/
PR merged Pattern Extractor org/conventions/
Meeting transcript Meeting Summarizer org/decisions/
Daily cron Curator deduplicate, flag contradictions
On write / cron Skill Maintainer org|project|user skills/
Weekly cron Skill Discoverer surfaces new skill suggestions
GROW

Event Agents

Write new knowledge to the wiki. Triggered by things that happen in your workflow — a release ships, a milestone closes, a PR gets merged. Each agent watches for a specific event and writes a structured summary into the right place.

Trigger: event fires
  • Release Summarizer
  • Milestone Summarizer
  • Pattern Extractor
CLEAN

The Curator

Keeps the wiki itself healthy. Runs on a schedule — not per write. Detects duplicate facts, flags contradictions between entries, and proposes merges. It never deletes anything unilaterally. It proposes, and a human approves.

Trigger: daily / weekly cron
  • Dedup facts
  • Flag contradictions
  • Propose merges
USEFUL

Skill Agents

Keep the query layer current. The Skill Maintainer watches for new wiki entries and routes them into the right skills automatically. The Skill Discoverer runs weekly and surfaces suggestions when patterns emerge.

Trigger: on write + weekly cron
  • Skill Maintainer
  • Skill Discoverer

Event agents grow the wiki. The curator keeps it clean. Skill agents keep it useful. Three jobs, intentionally separate.

Customer-Authored Prompts

You write the prompts. We run them in isolated Firecracker microVMs — ~125ms boot time, clean VM per run, no cross-customer contamination.

.vibe/agents.yaml
agents:
- name: release-summarizer
trigger: github.release
prompt: |
You are summarizing releases for a
medical scheduling SaaS. Focus on API
changes and breaking changes.
- name: linear-milestone
trigger: linear.milestone.completed
prompt: |
Summarize this milestone focusing on
what we decided NOT to build and why.

WHY VIBEDECODING

Lightning icon

STANDALONE CLI

Works with Claude Code, Cursor, Aider, any agent framework. No API integrations to maintain.

Target icon

SKILLS, NOT QUERIES

Agents call vibe skill code-review and get everything they need. Gets smarter over time without any agent changes.

Layers icon

LAYERED CONTEXT

Org, project, and user layers merge into one tailored skill. The same skill name returns different context depending on where you are.

Discovery icon

SKILL DISCOVERY

The system tells you what skills you should have, based on what you've already written.

Lock icon

GIT-BACKED TRUST

Agent-proposed changes go through PR review. Full provenance. Human-auditable at all times.

Shield icon

FIRECRACKER ISOLATION

Real VM-level isolation for agent execution. Genuinely safe to give write access to a wiki that matters.

Prompt owned icon

PROMPT-OWNED

You control the voice and focus of agents. We guarantee reliable, isolated execution.

Globe icon

CROSS-PROJECT SCOPE

The thing AGENTS.md can't do. Org-wide knowledge that spans every repo.

PRICING

Gate by run volume, not by agent type or feature access. All tiers get the same agents. Flat team tiers — no per-seat friction.

FREE
$0
forever
  • 1 user
  • 5 agent runs / month
  • CLI access
  • Git-backed wiki
Build the wiki habit with the CLI
TEAM
$39/mo
flat rate
  • Up to 15 users
  • 200 agent runs / month
  • All agent types included
  • $0.15 / overage run
Agents writing to your wiki automatically
ENTERPRISE
Custom
talk to us
  • Unlimited users
  • Custom run volume
  • All agent types included
  • SSO, audit logs
Your legal team calls our legal team
> LAUNCHING_SOON

GET EARLY ACCESS

We're building vibedecoding in the open. Sign up to be among the first teams to try it — and help shape what we build next.