Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
OpenCortex
Self-improving memory architecture for OpenClaw agents. Structured memory files, nightly distillation, weekly synthesis, enforced principles (P0 for custom,...
skill openclawclawhub Free
Self-improving memory architecture for OpenClaw agents. Structured memory files, nightly distillation, weekly synthesis, enforced principles (P0 for custom,...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- README.md, references/architecture.md, references/distillation.md, references/weekly-synthesis.md, scripts/git-backup.sh, scripts/install.sh
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 3.5.18
Provenance
- Publisher
- JD2005L
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
OpenCortex β Self-Improving Memory Architecture
Transform a default OpenClaw agent into one that compounds knowledge daily. π¦ Full source on GitHub β review the code, file issues, or contribute.
What This Does
Structures memory into purpose-specific files instead of one flat dump Installs nightly maintenance that distills daily work into permanent knowledge Installs weekly synthesis that catches patterns across days Establishes principles that enforce good memory habits β and backs them up with nightly audits that verify tool documentation, decision capture, sub-agent debriefs, failure analysis, and unnecessary deferrals to the user. Nothing slips through the cracks. Builds a voice profile of your human from daily conversations for authentic ghostwriting (opt-in, requires OPENCORTEX_VOICE_PROFILE=1) Encrypts sensitive data in an AES-256 vault with key-only references in docs; supports passphrase rotation (vault.sh rotate) and validates key names on vault.sh set Enables safe git backup with secret scrubbing (secrets never modified in your live workspace β scrubbed in an isolated copy only) Tracks growth over time (opt-in) β daily metrics snapshots with compound scoring and ASCII growth charts
Installation
Prerequisites (install these separately if you don't have them): OpenClaw 2026.2.x+ ClawHub CLI # 1. Download the skill from your OpenClaw workspace directory cd ~/clawd # or wherever your workspace is clawhub install opencortex # 2. Run the installer FROM YOUR WORKSPACE DIRECTORY (not from inside the skill folder) bash skills/opencortex/scripts/install.sh # Optional: preview what would be created without changing anything bash skills/opencortex/scripts/install.sh --dry-run The installer will ask about optional features (encrypted vault, voice profiling, infrastructure collection, git backup). It's safe to re-run β it skips anything that already exists. The installer itself makes no network calls β it only creates local files and registers cron jobs. # 3. Verify everything is working (read-only β checks files and cron jobs, changes nothing) bash skills/opencortex/scripts/verify.sh You can also ask your OpenClaw agent "is OpenCortex working?" β it knows how to run the verification and share results. The script will: Create the file hierarchy (non-destructively β won't overwrite existing files) Create directory structure Set up cron jobs (daily distillation, weekly synthesis) Optionally set up git backup with secret scrubbing After install, review and customize: SOUL.md β personality and identity (make it yours) USER.md β info about your human MEMORY.md β principles (add/remove as needed) .secrets-map β add your actual secrets for git scrubbing
Updating
# 1. Download the latest version (run from workspace root) clawhub install opencortex --force # 2. Re-run the installer β it detects your existing install and offers to update bash skills/opencortex/scripts/install.sh The installer detects your existing version and offers three options: Update (recommended), Full reinstall, or Cancel. The update path is non-destructive β it adds missing content, refreshes cron messages, and offers any new optional features without overwriting your customized files.
Architecture
SOUL.md β Identity, personality, boundaries AGENTS.md β Operating protocol, delegation rules MEMORY.md β Principles + memory index (< 3KB, loaded every session) TOOLS.md β Tool shed: APIs, scripts, and access methods with abilities descriptions INFRA.md β Infrastructure atlas: hosts, IPs, services, network USER.md β Human's preferences, projects, communication style BOOTSTRAP.md β First-run checklist for new sessions memory/ projects/ β One file per project (distilled, not raw) contacts/ β One file per person/org (role, context, preferences) workflows/ β One file per workflow/pipeline (services, steps, issues) runbooks/ β Step-by-step procedures (delegatable to sub-agents) preferences.md β Cross-cutting user preferences by category archive/ β Archived daily logs + weekly summaries YYYY-MM-DD.md β Today's working log (distilled nightly)
Principles (installed by default)
#NamePurposeP1Delegate FirstAssess tasks for sub-agent delegation; stay availableP2Write It DownCommit to files, not mental notesP3Ask Before ExternalConfirm before emails, public posts, destructive opsP4Tool Shed & WorkflowsDocument tools and workflows; enforced by nightly auditP5Capture Decisions & PreferencesRecord decisions and preferences; enforced by nightly + weekly auditP6Sub-agent DebriefDelegated work feeds back to daily log; orphans recovered by distillationP7Log FailuresTag failures/corrections; root cause analysis enforced by nightly auditP8Check the Shed FirstConsult TOOLS.md/INFRA.md/memory before deferring work to user; enforced by nightly audit
Cron Jobs (installed)
ScheduleNameWhat it doesDaily 3 AM (local)DistillationReads daily logs β distills into project/tools/infra files β audits tools/decisions/debriefs/failures β optimizes β archivesWeekly Sunday 5 AMSynthesisReviews week for patterns, recurring problems, unfinished threads, decisions; auto-creates runbooks from repeated procedures Both jobs use a shared lockfile (/tmp/opencortex-distill.lock) to prevent conflicts when daily and weekly runs overlap. Customize times by editing cron jobs: openclaw cron list then openclaw cron edit <id> --cron "...".
Git Backup (optional)
If enabled during install, creates: scripts/git-backup.sh β auto-commit every 6 hours, scrubs secrets in an isolated temp copy (workspace files never modified) .secrets-map β maps secrets to placeholders (gitignored, 600 perms) Add secrets to .secrets-map in format: actual_secret|{{PLACEHOLDER_NAME}} Before each push, git-backup.sh verifies no raw secrets remain in the scrubbed copy. If any are found, the backup is aborted β nothing reaches the remote.
Customization
Adding a project: Create memory/projects/my-project.md, add to MEMORY.md index. Adding a contact: Create memory/contacts/name.md. Distillation auto-creates contacts from conversations. Adding a workflow: Create memory/workflows/my-pipeline.md. Distillation auto-creates workflows when described. Adding a preference: Append to memory/preferences.md under the right category. Distillation auto-captures from conversation. Adding a principle: Append to MEMORY.md under π΄ PRINCIPLES. Keep it short. Adding a runbook: Create memory/runbooks/my-procedure.md. Sub-agents can follow these directly. Adding a tool: Add to TOOLS.md with: what it is, how to access it, and a goal-oriented abilities description (so future intent-based lookup matches).
How It Compounds
Daily work β daily log β nightly distill β routes to project/tools/infra/principles files β optimization pass (dedup, prune stale, condense) β weekly synthesis β patterns, recurring problems, unfinished threads β auto-creates runbooks from repeated procedures β `memory/runbooks/` Sub-agent work β debrief (P6) β daily log β same pipeline Decisions β captured with reasoning (P5) β never re-asked New tools β documented with abilities (P4) β findable by intent Each day the agent wakes up slightly more knowledgeable and better organized.
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
4 Docs2 Scripts
- README.md
- references/architecture.md
- references/distillation.md
- references/weekly-synthesis.md
- scripts/git-backup.sh
- scripts/install.sh