| name | lorekeeper-marketing |
| description | Marketing workflow for Lorekeeper — README copy, manifesto, positioning, and multi-agent A/B testing of copy variations. Load this when working on any user-facing content: README, docs/manifesto.md, positioning, comparison tables, or launch copy.
|
| version | v1.0.0 |
| tags | ["marketing","readme","positioning","ab-testing"] |
| related_skills | ["lorekeeper-pm","deep-research"] |
Lorekeeper Marketing
User-facing content workflow for the Lorekeeper project.
Core Principles
All Lorekeeper marketing copy must follow these non-negotiables:
- Don't burn bridges — tech ecosystems thrive when there's a lot of contribution from open
source and adoption. Never undermine competing tools. Acknowledge them by name where relevant;
name-dropping peers is generous, not threatening.
- Cooperative tone always — even in comparison tables. Frame differences as trade-offs, not
deficiencies. "Optimised for X" beats "worse at Y".
- Own our strengths, don't exaggerate — local-first, self-improving quality loop, zero ops,
built by agents using agents, free to run forever. These are real. Lead with them.
- Honest about trade-offs — the 1.4GB model weight is real. Benchmarks pending. Cloud not
yet available. Say so upfront. Trust compounds when you don't oversell.
- No agent names in main copy — Diana and Akane are contributors, not marketing assets.
Credits section only (end of doc), never in hero or manifesto body.
Key Positioning
Tagline: Self-improving memory for AI agents. One command, no cloud, no config.
The mechanism that makes us different:
Agent uses a memory → rates it useful or not →
scores adjust automatically → weak memories fade →
strong memories surface more often → search gets sharper
A six-month-old install is genuinely different from a fresh install. Nobody else has this.
Our niche: Solo developers and agent workflows where zero ops, zero cloud, and a
self-improving store matter most. Cloud services and Docker-based solutions serve teams and
production apps well — we're the other end of that spectrum.
Manifesto location: docs/manifesto.md — the short public-facing statement of values.
Positioning deep-dive: docs/positioning-manifesto.md — internal strategy reference.
README Structure (canonical order)
- Hero block — tagline + install command + one-liner hook
- Why Lorekeeper — problem story, cooperative landscape framing, our niche
- Quick Start — install → setup → connect → first memory
- Use Cases — 4 scenarios (session continuity, multi-agent, debugging, onboarding)
- Who It's For — explicit in/out
- How It Compares — table with cooperative framing sentence above and below
- Features table
- MCP Tools — full API reference
- Performance — benchmarks (LKPR-70) or honest stub
- Dashboard — screenshots
- Built by Agents — dogfooding story
- Setup (git clone) — dev path
- Development — test/lint commands
- Project Layout
- License
- Footer — links to manifesto + strategy docs
Competitor Research Protocol
Before any major README or manifesto update, research the current state of:
- agentmemory (rohitg00/agentmemory) — Node-based, hybrid search, self-described #1
- mem0 (mem0ai/mem0) — YC S24, arXiv-backed, cloud + library, benchmark leader
- basic-memory (basicmachines-co/basic-memory) — file-based, strong testimonials
- phloem (CanopyHQ) — strongest hero copy in the space as of mid-2026
Use delegate_task with toolsets: ["web", "browser"] for parallel pulls.
Extract: README structure, benchmark claims, marketing patterns, tone.
Never copy — use as inspiration and contrast only.
A/B Testing Copy Variations
Evaluate headline copy, manifesto variations, or README rewrites.
Step 1 — Write 3 variations
Name each after its rhetorical stance: The Craftsperson (tool-focused, humble specifics), The Ecosystem Builder (community-focused, vision-forward), The Practitioner (developer-native, leads with install).
Step 2 — Run 11 evaluator personas via delegate_task
Split into 3 parallel subagent calls (4 + 4 + 3). Each evaluates all variations but votes as its assigned persona(s). Voting prompt: "Vote: A, B, or C. 2-3 sentence reasoning. Focus on [persona-specific lens]."
Personas: 1. Skeptical senior engineer, 2. Junior dev first AI project, 3. AI researcher, 4. Open source maintainer, 5. Privacy-conscious developer, 6. Developer advocate, 7. Multi-agent systems builder, 8. Hacker News front-pager, 9. An actual AI agent, 10. Startup founder, 11. Potential contributor.
Step 3 — Tally and synthesise
Count votes. Note why dissenters voted differently. Winning variation is the base; borrow specific elements from runners-up.
Step 4 — Write the merged final
Always integrate the best 1-2 elements from runners-up before shipping.
Comparison Table Guidelines
Always open the table with:
"There are great tools in this space — each makes different trade-offs. Here's where
Lorekeeper sits:"
Always close with:
"[Cloud/Docker/library solutions] are strong choices for [their niche]. Lorekeeper is
optimised for [our niche] — [our key props]."
Never use ❌ to mean "bad". Use it only for "this genuinely doesn't have this feature".
If a competitor has a paid version of something we offer free, say "Paid" not ❌.
Tone Reference
Do: "Weak memories fade, strong ones rise."
Do: "When the agents that build it depend on it, the incentives are right."
Do: "We're grateful to be part of that conversation."
Do: "We're honest about trade-offs. The 1.4GB model is real."
Don't: "Unlike other solutions, Lorekeeper..."
Don't: "The only memory server that..."
Don't: Grand vision openers ("The future of AI depends on...")
Don't: Agent names (Diana, Akane) in hero copy or manifesto body
Files Owned by This Workflow
| File | Purpose |
|---|
README.md | Primary marketing surface |
docs/manifesto.md | Short public values statement |
docs/positioning-manifesto.md | Internal strategy (not linked prominently) |
docs/screenshots/ | Screenshot assets for README |
Screenshots source of truth: assets/ — copies placed into docs/screenshots/ for README refs.
Branch Convention
Marketing changes go on: chore/LKPR-N-<slug>
Commit prefix: [LKPR-N] chore: <description>
PR body: Refs #N (never Closes #N for chore/proposal PRs)
