myICOR vs Scribe

myICOR and Scribe are both productivity tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

myICOR

The system is a local markdown folder pre-loaded with a six-person AI team: a routing orchestrator (Larry), a research specialist (Pax), a capture agent (Penn), and others — each with a named contract and a session journal so the next model picks up where the last one left off. You bring your own LLM; the folder supplies the memory. Research produces structured notes in place, drafts inherit your established voice, and weekly review prompts surface stale items automatically. The ceiling appears when you need real-time data, API integrations, or collaborative editing — none of that is in the folder. Teams that need those reach for purpose-built tools alongside this one.

Scribe

The pipeline runs in three stages — capture from git repos, Claude Code/Codex sessions, iMessage-dropped URLs, and drop files; triage via keyword-density scoring before any LLM call touches the input; then compile into a typed-graph wiki of plain markdown with auto-generated wikilinks and backlinks. FTS5 pre-filtering means sessions with nothing worth keeping cost zero API tokens. The vendor states the full pipeline runs against a local Ollama server with one line changed in scribe.yaml, eliminating API spend entirely. Where it strains: the system is only as useful as the agent's ability to query the KB — if your agent doesn't read CLAUDE.md or AGENTS.md on startup, the handshake Scribe writes is ignored. Teams adopting this commit to a local-first, terminal-native workflow; there is no hosted dashboard or GUI to inspect what Scribe wrote.

Attribute	myICOR	Scribe
Pricing	Paid	Free
Free trial	No	No
Open source	No	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	Local disk (any OS with markdown support)	macOS, Linux (Go binary)
Pros	LLM-agnostic folder architecture, so switching from Claude to Gemini mid-project is a matter of opening the same folder in a different app — no re-pasting context, no lost session history. Persistent agent journals mean each specialist picks up from the last session, so you stop spending the first ten minutes of every AI conversation re-explaining who you are and what you're working on. Plain markdown on your local disk means zero migration risk — if the vendor disappears tomorrow, every note, contract, and workflow you built is still readable by any text editor or LLM. Larry's routing layer matches requests to the right specialist automatically, so you don't have to remember which prompt style triggers good research versus good drafting — the team handles the handoff. Open-source scaffold under CC BY-NC-SA 4.0, so you can inspect, fork, and extend the agent contracts without waiting on a vendor roadmap or paying for access to the base system.	FTS5 pre-filtering rejects low-value sessions before any LLM call, so zero-insight sessions cost zero tokens — which means running the pipeline daily against a local Ollama server produces no API bill and no noise in the output corpus. The CLAUDE.md and AGENTS.md handshake injection means every new agent session in every project queries prior decisions automatically, so agents stop proposing the library you already evaluated and rejected two projects ago. A typed 10-kind edge schema (supersedes, contradicts, derived_from, and others) connects articles relationally, so the KB captures decision lineage rather than just a flat pile of notes that have no memory of which choice replaced which. One flag in scribe.yaml switches the entire pipeline to a local Ollama server, which means you can run extraction, absorb, and Dream consolidation with zero external API dependency and no data leaving your machine. Output is plain markdown in a git repo you control, so the corpus survives any change to Scribe itself — open it in Obsidian, VS Code, or vim, push it to Gitea or Forgejo, and no vendor has leverage over your data.
Cons	The folder has no mechanism for live data: API calls, web scraping, calendar reads, and CRM syncs are all outside its scope. Teams that need agents to pull live information must wire up a separate integration layer and maintain it alongside the folder — which is a second system to debug. There is no multi-user collaboration model. Two people cannot edit the same folder simultaneously with conflict resolution. Teams of more than one person sharing a PKM workspace hit this wall immediately and typically move the shared layer to a tool with real-time sync — Notion, Obsidian Sync, or a shared Git repo — while keeping individual folders local. No hosted inference or built-in LLM access means every new user must already have API credentials or a local model running before the team scaffold does anything. For non-technical users who came for the AI workflows, the setup friction before first use is real and the docs leave meaningful configuration detail to the user to figure out. The agent team is fixed at the scaffold level — expanding it requires running Nolan's eight-step hiring procedure, which is a prompt-driven workflow inside the folder. Teams used to GUI-based agent builders who want to add a specialist in two clicks will find the process slower and more text-heavy than competing tools that offer visual agent creation.	The handshake only works if the agent reads CLAUDE.md or AGENTS.md at session start — agents or wrappers that skip that file ignore every decision Scribe wrote, and there is no fallback mechanism to force context injection, so teams with non-standard agent setups get no benefit from the KB without manual wiring. Scribe is a single-developer local tool with no multi-user access model: one machine, one corpus, one git repo. Teams of two or more who need shared architectural memory hit this wall immediately and end up running separate personal instances while syncing decisions by hand — at which point they are maintaining the problem Scribe was supposed to solve. The Dream consolidation cycle runs on a fixed cron schedule (weekly, Sundays at 02:00 per the docs), so a decision made Monday that contradicts a decision made Friday won't be cross-linked until the next consolidation window — teams working fast on interrelated projects find the KB is always one cycle behind the work. There is no GUI, no hosted dashboard, and no search UI outside the terminal qmd command or Claude Code's MCP integration — teams whose product managers or non-engineering stakeholders need to read the KB have no access path without standing up a separate rendering layer like mdbook or Obsidian.

Bottom line

MyICOR is paid while Scribe is free; Scribe is open source. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between myICOR and Scribe?

myICOR is Paid, while Scribe is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is myICOR better than Scribe?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.

myICOR vs Scribe: which should I pick?

Pick myICOR if its pricing model, openness, or platform fit matches your constraints; pick Scribe otherwise. Check free-trial availability on each listing if you want to test before committing.

Comparison data is sourced and verified by the AIDiveForge data pipeline. AIDiveForge is editorially independent.