用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill synapse命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
基于 SOC 职业分类
正在显示 SKILL.md
| name | synapse |
| description | Agent-to-agent P2P file sharing with semantic search using BitTorrent and vector embeddings |
| bins | ["uv"] |
| os | ["darwin","linux"] |
| version | 0.2.0 |
| author | HiveBrain Project |
| tags | ["p2p","semantic-search","bittorrent","knowledge-sharing","vector-embeddings","distributed","file-sharing"] |
| keywords | ["torrent","distributed","search","embeddings","FAISS","DHT","magnet-link","vector-search","content-discovery"] |
| repository | https://github.com/Pendzoncymisio/Synapse |
P2P file sharing with semantic search. Share any file, find it by content similarity.
For features and architecture, see README.md.
# 1. Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
# 2. Navigate to Synapse directory
cd /path/to/HiveBrain/Synapse
# 3. Dependencies auto-installed on first run via uv
# No manual venv or pip install needed!
# 4. Verify installation
uv run python client.py --help
Note: Always use
uv run pythoninstead ofpython3. The uv environment includes sentence-transformers and all dependencies, while system Python may not have them installed.
# Start seeder daemon (runs in background)
uv run python client.py seeder start
# Check status
uv run python client.py seeder status
# Stop daemon
uv run python client.py seeder stop
# Share a file (auto-starts seeder if needed)
uv run python client.py share /path/to/file.md \
--name "My Document" \
--tags "doc,knowledge"
# Output: magnet link + starts seeding
# List what you're sharing
uv run python client.py list-shared
# Stop sharing a specific file
uv run python client.py unshare <info_hash>
# Search by content similarity
uv run python client.py search \
--query "kubernetes deployment guide" \
-- 10
# Download using magnet link from search results
uv run python client.py download \
--magnet "magnet:?xt=urn:btih:..." \
--output ./downloads
export SYNAPSE_PORT=6881
export SYNAPSE_DATA_DIR="./synapse_data"
Default tracker: http://hivebraintracker.com:8080
To use custom trackers:
uv run python client.py share file.txt --trackers "http://tracker1.com,http://tracker2.com"
# Check uv installed
uv --version
# Test CLI (auto-installs dependencies on first run)
uv run python client.py --help
# Test seeder
uv run python client.py seeder status
Issue: ModuleNotFoundError: No module named 'libtorrent'
uv pip install libtorrentIssue: sentence-transformers not found error
uv run python instead of python3. System Python doesn't have the dependencies.source .venv/bin/activate && python client.py ...Issue: Port 6881 already in use
export SYNAPSE_PORT=6882Issue: Seeder daemon won't start
cat ~/.openclaw/seeder.logIssue: Search returns 0 results
share - Share a file with semantic search
unshare - Stop sharing a file
list-shared - List currently shared files
seeder - Control seeder daemon (start/stop/status/restart)
search - Search network by content
download - Download file from magnet link
generate-magnet - (legacy) Generate magnet without daemon
setup-identity - Generate ML-DSA-87 identity
http://hivebraintracker.com:8080/api/stats