Akashic Records

℗ 2026 Colossal Capital · managed SaaS

Any repo becomes a Collection.
Claude Fables are why we built the studio.

Connect any Git repository — legacy monolith, greenfield service, Cursor project, or a Claude Fable you vibe-coded in one session. Each repo is a Collection. Group related repos into a Library. Span entities in a Workspace. Then mix and publish from the studio with your team and identity-provisioned AI agents.

Fables aren't every repo. They're the new Claude output format — sprawling one-shots that work once but need a path to iteration. Akashic Records is built for that moment and for every other codebase you already have.

one pressing · record · liner · coffee-table book · five source layers

One-shot masterpieces need a label, not a landfill

Anthropic just shipped Fable — and teams are generating complete applications in a single session. Those repos are real code with real architecture buried inside a vibe-coded spike. They aren't the only thing Akashic handles, but they're the urgent case: a massive one-shot that has to become iterable, team-owned, and deployable.

What a Collection is

Any repository you connect — Fable or not — mastered as one pressing: a record (code), a liner (voice + provenance), and a coffee-table book (tickets + docs).

One repo, one pressing — three artifacts

Mastering doesn't flatten your repo into a file tree. Each Collection ships as a boxed set: the record agents spin (source + codemap), the liner that preserves how it was made (voice + skillfiles), and the coffee-table book your team actually reads (tickets, docs graph, reconciliation). All three draw from the same five source layers — repo, voice, tickets, documentation graph, and codemap.

Artifact I · record

Spin the code

RAG index, analysis passes, codemap, deployments — what producers and CI run against.

RepoSource tree, branches, modules, commits
CodemapArchitecture fingerprint, ripple-risk graph
MasteringIndex, classify, cleanup, code analysis, deployment
Artifact III · book

Open the volume

Ticket matrix, doc navigation, graph explorer, reconciliation gate — the PM artifact product and eng share.

TicketsLinear, Jira, GitHub — generated, deduped, gated
Docs graphConsolidated docs, coverage scores, cross-links
ArchiveVersioned docs run to cloud storage per pass

This maps to how Akashic is built. Nineteen Prefect mastering phases populate each artifact — not decorative labels. Mature repos fill the book first; Claude Fables flood the liner until tickets catch up. Same pressing, different balance.

Collection, Library, Workspace

Three terms in the product. A Collection is one pressing — record, liner, book. Library and Workspace scale how many pressings you work with at once.

01 · REPO

Collection

One repository — mastered into record, liner, and coffee-table book from repo, voice, tickets, documentation graph, and codemap.

Metaphor: one boxed pressing — not one track.
02 · ENTITY

Library

Multiple Collections under the same entity — API, web, contracts, infra — shared run history and one reconciliation gate.

Metaphor: an album from one session.
03 · CROSS-ENTITY

Workspace

Collections across different entities in one collaborative environment — your org, a client, a portfolio company.

Metaphor: the full roster in one studio.

The studio is the collaborative portal (web or VS Code) where your team works inside a Workspace. Product name stays Workspace; the studio is the room you work in.

Multiple repos, one entity, one Library

Fables especially rarely stay in one repo — but neither do most real products. Group every related Collection into a Library and run mastering, reconciliation, and agent work across the full stack.

collection/payments-apiindexed
collection/payments-webindexed
collection/shared-contractssyncing
collection/deploy-confignew

library · payments · 4 collections

Cross-collection graph

Relationships span every Collection in the Library — see ripple effects before anyone merges.

Unified reconciliation

Tickets dedupe against Linear, Jira, and GitHub across the whole Library. One gate.

Library-scoped producers

Agents per Collection with shared Library context — the whole album, not one track.

Where teams publish from one Workspace

The studio is Akashic's collaborative cloud portal and VS Code extension. Engineers run analyses and review agent PRs; product approves at the reconciliation gate — whether the Collection started as a Fable or shipped years ago.

Web portal

Mastering passes, Prefect run history, RAG chat, ticket matrix, agent approvals, deployments — no install.

Open your Workspace →

VS Code extension

Connect Collections, run analysis, semantic search — step into the full studio when you need the whole Workspace.

VS Code Marketplace →

RAG chat with citations

Answers from indexed Collections via Weaviate — file paths, not model memory.

Derived skill profiles

SKILL.md profiles from each Collection's conventions, stored in your Workspace.

Managed CI/CD

Tekton pipelines: builds, scans, signing, SBOMs — routed to your targets.

Human-in-the-loop queue

Approvals for syncs, mutations, and deployments — policies you control.

Nineteen phases — each lands on an artifact

Run full_analysis from the studio or VS Code. Prefect on Apollo writes into your pressing: code phases on the record, provenance on the liner, PM and docs on the book.

Record

Index, classify, analyze, deploy — the executable substrate.

12 phases
ARskillfiles

Liner

Voice sessions + emit_skillfiles — how it was made.

1 phase + voice ingest

Book

Docs, PM context, tickets, archive — what teams reconcile.

5 phases
Record code · codemap · deploy Liner voice · skillfiles · provenance Book tickets · docs · reconciliation Both knowledge graph → codemap + explorer
IndexRecordRAG into Weaviate, tenant-scoped
ClassifyRecordarchitecture map, stack fingerprint
DuplicatesRecordcopy-paste blocks, redundant files
CleanupRecorddead code, stale dependencies
Code analysisRecordsecurity, quality, coverage per file
ScaffoldingRecordmissing structure gaps
DocumentationBookcoverage scoring per module
Docs consolidationBookmerge scattered docs
Script intelligenceRecordCI configs, Makefiles
Folder intelligenceRecordmodule integration gaps
PM contextBookLinear / Jira / GitHub tickets ingested
Emit skillfilesLinerderive SKILL.md from conventions
Knowledge graphBothcodemap on record · graph explorer in book
Generate ticketsBookper-file IDs, gated before sync
DeploymentRecordDocker, K8s, Terraform artifacts
Understand repoRecordpurpose, patterns, debt
Restructuring planBooksynthesized readable plan from analysis
Drift analysisRecordsemantic drift since last snapshot
Docs archiveBookversioned run to cloud storage

Identity-provisioned agents per Collection

Dedicated AI producers on each Collection — MCP tools through Apollo, Auth0 machine identities, scoped OAuth, Cloudflare Signed Agents audit trails.

🎛

Mix Engineer

Tickets → code → tests → draft PRs on akashic/*.

🔊

Mastering Engineer

Coverage checks, regressions, gap tickets when quality drops.

📀

Catalog Manager

Rebuilds graph and docs archive after every merge.

Four steps to your first Collection

  1. 01
    Create an accountSign up at the CC keys portal. One API key for the studio and VS Code.
  2. 02
    Activate your tenantManaged Apollo infrastructure — nothing to install or host.
  3. 03
    Connect your reposAny Git repo becomes a Collection. Got a Claude Fable? Start there. Group into Libraries, span entities in a Workspace.
  4. 04
    Enter the studioReview tickets at the reconciliation gate, approve work, let the producers ship.

Platform fee + passthrough inference

Akashic itself is free — you pay for the Apollo tenant that runs your studio, and for the LLM tokens you actually consume. No hidden markup when you bring your own keys.

$0 for Akashic — studio, mastering, portal, VS Code
$5/mo Apollo — Prefect, Weaviate, tenant storage

What the platform covers

The Akashic product — Collections, Libraries, Workspaces, nineteen-phase mastering, ticket reconciliation, and the studio portal — ships at $0. Apollo is the managed backbone at $5/mo per tenant.

  • Repo indexing, knowledge graph, and codemap
  • Prefect orchestration and run history
  • Identity-provisioned agents and reconciliation gate

BYOK — bring your own key

Connect your own API keys in the studio. Inference routes through your account; Akashic never resells your quota.

Anthropic OpenAI Google Gemini Together AI Hugging Face Groq Fireworks DeepSeek OpenRouter

Colossal Capital tier sets limits across every product — API calls, repos, training jobs, team size. Tier details · sign up