[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M778D6BWMFA20WS72DB0298K":3,"skill-same:01M778D6BWMFA20WS72DB0298K":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M778D6BWMFA20WS72DB0298K","valence-memory",null,"javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzonk1024\u002Fvalence-memory\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# Valence Memory\n\nPersistent knowledge substrate for OpenClaw. Replaces flat-file memory with confidence-scored beliefs, semantic search, pattern recognition, and federated knowledge sharing.\n\n## What It Does\n\nValence gives your agent **real memory** — not conversation logs, but a structured knowledge base that grows smarter over time:\n\n- **Beliefs** — Factual statements with dimensional confidence scores, domain classification, and provenance tracking\n- **Auto-recall** — Relevant beliefs are injected into context before the agent runs, no manual searching needed\n- **Auto-capture** — Insights from conversations are extracted as beliefs automatically\n- **Patterns** — Recurring behaviors and preferences are detected across sessions\n- **Entities** — People, tools, projects, and concepts tracked with relationships\n- **Tensions** — Contradictions between beliefs are surfaced for resolution\n- **Sessions** — Full conversation lifecycle tracking with exchange recording\n- **MEMORY.md sync** — Disaster-recovery fallback so you lose nothing if you uninstall\n\n## Prerequisites\n\nValence requires a running server with PostgreSQL + pgvector:\n\n```bash\n# Install Valence\npip install ourochronos-valence\n\n# Start PostgreSQL with pgvector (Docker is easiest)\ndocker run -d --name valence-db \\\n  -e POSTGRES_DB=valence \\\n  -e POSTGRES_USER=valence \\\n  -e POSTGRES_PASSWORD=valence \\\n  -p 5432:5432 \\\n  pgvector\u002Fpgvector:pg17\n\n# Run migrations\nvalence-server migrate up\n\n# Start the server\nvalence-server\n```\n\nThe server runs at `http:\u002F\u002F127.0.0.1:8420` by default.\n\n## Install the Plugin\n\n```bash\nopenclaw plugins install @ourochronos\u002Fmemory-valence\n```\n\n## Configure\n\nAdd to your OpenClaw config (`~\u002F.openclaw\u002Fopenclaw.json`):\n\n```json\n{\n  \"plugins\": {\n    \"slots\": {\n      \"memory\": \"memory-valence\"\n    },\n    \"entries\": {\n      \"memory-valence\": {\n        \"enabled\": true,\n        \"config\": {\n          \"serverUrl\": \"http:\u002F\u002F127.0.0.1:8420\",\n          \"autoRecall\": true,\n          \"autoCapture\": true,\n          \"sessionTracking\": true,\n          \"memoryMdSync\": true\n        }\n      }\n    }\n  }\n}\n```\n\nOr use the OpenClaw Control UI to configure via the web interface.\n\n### Configuration Options\n\n| Option | Default | Description |\n|--------|---------|-------------|\n| `serverUrl` | `http:\u002F\u002F127.0.0.1:8420` | Valence server URL |\n| `authToken` | — | Bearer token (or set `VALENCE_AUTH_TOKEN` env var) |\n| `autoRecall` | `true` | Inject relevant beliefs before agent runs |\n| `autoCapture` | `true` | Extract insights from conversations |\n| `sessionTracking` | `true` | Track OpenClaw sessions in Valence |\n| `exchangeRecording` | `false` | Record individual conversation turns |\n| `memoryMdSync` | `true` | Sync beliefs to MEMORY.md as DR fallback |\n| `recallMaxResults` | `10` | Max beliefs injected on auto-recall |\n| `recallMinScore` | `0.5` | Minimum relevance score for recall (0-1) |\n\n## Agent Tools\n\nThe plugin exposes 58 tools organized by category:\n\n### Core (used most often)\n- `belief_create` \u002F `belief_query` \u002F `belief_search` \u002F `belief_get` — Create and find beliefs\n- `belief_supersede` — Update a belief while preserving history\n- `belief_archive` — Archive a belief (GDPR-compliant, maintains chain)\n- `confidence_explain` — Understand why a belief has its confidence score\n- `entity_search` \u002F `entity_get` — Find and inspect entities\n- `tension_list` \u002F `tension_resolve` — Surface and resolve contradictions\n- `insight_extract` — Extract an insight from conversation into a belief\n- `pattern_search` \u002F `pattern_record` \u002F `pattern_reinforce` — Behavioral patterns\n- `memory_search` \u002F `memory_get` — Search and read MEMORY.md (DR fallback)\n\n### Sharing & Federation\n- Share beliefs with trusted peers, query across federated nodes\n- Trust verification, reputation tracking, dispute resolution\n- Backup export\u002Fimport for portability\n\n### VKB (Virtual Knowledge Base)\n- Session lifecycle management\n- Exchange recording\n- Advanced pattern and insight tools\n\n## How It Works\n\n1. **On each agent turn**, auto-recall searches Valence for beliefs relevant to the current conversation and injects them as context\n2. **During conversations**, the agent uses belief tools to capture decisions, preferences, and insights\n3. **After conversations**, auto-capture extracts any uncaptured insights\n4. **Over time**, beliefs accumulate confidence through corroboration, patterns emerge from repeated observation, and the agent's understanding deepens\n5. **MEMORY.md** is kept in sync as a human-readable snapshot and safety net\n\n## Architecture\n\n```\nOpenClaw Agent\n    ↕ (plugin tools + hooks)\nmemory-valence plugin\n    ↕ (REST API)\nValence Server (http:\u002F\u002F127.0.0.1:8420)\n    ↕ (SQL + pgvector)\nPostgreSQL + pgvector\n```\n\nThe plugin is a thin REST client. All intelligence lives in the Valence server — embeddings, confidence scoring, pattern detection, and federation protocol.\n\n## Links\n\n- **Valence**: [github.com\u002Fourochronos\u002Fvalence](https:\u002F\u002Fgithub.com\u002Fourochronos\u002Fvalence) | [PyPI](https:\u002F\u002Fpypi.org\u002Fproject\u002Fourochronos-valence\u002F)\n- **Plugin**: [github.com\u002Fourochronos\u002Fvalence-openclaw](https:\u002F\u002Fgithub.com\u002Fourochronos\u002Fvalence-openclaw) | [npm](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@ourochronos\u002Fmemory-valence)\n- **Issues**: [github.com\u002Fourochronos\u002Fvalence\u002Fissues](https:\u002F\u002Fgithub.com\u002Fourochronos\u002Fvalence\u002Fissues)\n",{},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fzonk1024\u002Fvalence-memory",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill valence-memory",{"tool":37,"command":38},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill valence-memory",{"tool":40,"command":41},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill valence-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzonk1024\u002Fvalence-memory\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]