agentic-kb
Make decisions and context travel at the same speed as creation.
AI-native knowledge ops. Vendor-neutral. No database. Lives in your repo.
- "We're shipping more than ever and feel blurrier about where we're going."
- "I can't review every direction fast enough to say yes or no."
- "My agents are aligned with me. Yours are with you. We're not aligned with each other."
- "By the time leadership catches up, another three things got built."
The real problem
Your agents made you 10× faster at creating. Nothing made you faster at deciding. The bottleneck didn't move to design, quality, or testing.
It moved to convergence.
Creation at agent speed. Decisions at human speed. That gap is where budgets burn, alignment erodes, and smart teams end up running in three directions at once.
agentic-kb is the piece of the fix that puts decisions, ideas, goals, and context on the same rails as the output — so a human at any level can stay in the loop with a swarm of agents and a team of other humans, without becoming the bottleneck.
Why it's built this way
🗂 No database
Plain Markdown in a git repo. Your KB versions like code, reviews like code, diffs like code. If a folder can read it, this works.
☁️ No cloud backend
No SaaS. No auth. No infra. Your knowledge stays on your disk. If the vendor disappears tomorrow, your KB is still there.
🔓 No vendor lock-in
Claude Code, VS Code Copilot, OpenCode — same skill, same contract, one install. No "Claude memory" trap. No "upgrade to Pro to access your own notes."
🪶 Lean by construction
One spec. Two reference skills. One reference agent. One installer. Install in 60s. Rip it out in 5 if it's not for you.
Five layers, one command
Only the personal layer is required. Higher layers are opt-in. Content flows up via promote, down via digest. Every boundary passes a five-question evaluation gate.
promote → ← digest
The evaluation gate
Applied at every persistence boundary. This is the system's immune system — nothing persists without earning its place.
- Does this strengthen a position?
- Does this inform a decision?
- Would you reference this again?
- Is this actionable?
- Does this already exist?
Four kinds of memory
findings/
Dated, immutable snapshots. The evidence base.
topics/
Living positions. Updated in place with changelog.
ideas/
Incubation objects. Seed → growing → ready → shipped.
foundation/
Identity: who you are, your context, sources, stakeholders.
One command: /kb
The agent infers the layer and action from context. No subcommand memorization needed.
/kb [text] — capture + evaluate
/kb review — process inbox
/kb promote — push to team
/kb digest team — pull team changes
/kb idea [text] — create idea
/kb develop [idea] — sparring session
/kb decide [desc] — open decision
/kb start-day — morning briefing
/kb end-week — weekly summary
/kb present [topic] — HTML slides
/kb setup — onboarding wizard
Decisions & ideas as first-class objects
Decisions
Tracked with evidence trails, stakeholders, RACI, and due dates. Not buried in prose.
gathering-evidence → under-discussion → proposed → decided → archive
Ideas
Observations with novelty value get incubated. The agent plays devil's advocate via /kb develop.
seed → growing → ready → shipped | archived
Cross-agent portable
One source of skills and agents feeds three harnesses. Write once, use everywhere.
Claude Code
.claude/skills/
VS Code Copilot
.github/skills/
OpenCode
.opencode/skills/
Get started
Claude Code
/install-marketplace https://github.com/wlfghdr/agentic-kb
/kb setupVS Code
// settings.json → chat.plugins.marketplaces
["wlfghdr/agentic-kb"]
// then: /kb setupOpenCode
scripts/install --target opencode --global
# then: /kb setupThat's it. /kb setup walks you through everything — name, role, workstreams, branding, integrations.