pi-deepseek-search
Web search for Pi using DeepSeek's server side search. Only works with DeepSeek models.
$ pi install npm:pi-deepseek-searchPackage Catalog
Extensions, skills, prompt templates, and themes published to npm. Install with pi install npm:<package>. See the package docs for details.
Recently published
@minhduydev/pi-subagentsHerdr-native delegation runtime for Pi with durable task state, foreground/background agents, worktree isolation, claims/lease heartbeats, evidence and independent review gates, grouped completion, schedules, RPC v3, recovery, and SDK/tmux fallback. Runti19m ago@gamalan/pi-gatewayMulti-platform chat bridge for pi — connect your AI agent to Telegram, Discord, Slack, and more. Real-time streaming, per-chat sessions, and role-based access control.38m agopi-cc-extensionsA Pi productivity suite with Claude Code-style UI, structured questionnaires, context inspection, and agent/session references40m agopi-privacyPrivacy posture + TEE attestation for Pi providers: cryptographically verified confidential-enclave (TEE) inference, enforced/labeled zero-data-retention (ZDR), and on-device detection — honestly graded so a verified guarantee never reads like a claimed o40m ago@danypops/papyrusDaemon-backed graph artifacts, evidence-bearing tasks, rules, skills, and native TUI workflows for Pi40m ago@arcaneorion/pi-provider-managerVisual config panel for models.json + roundrobin failover engine + provider health stats for pi coding agent43m ago@remnic/plugin-piRemnic memory extension for Pi Coding Agent58m ago@mammothb/pi-memoryVCC conversation compaction for Pi, backed by mm-cli1h ago
All packages
1-36 / 36 (of 5323)
@alexanderfortin/pi-deepseek-usage
Pi extension for monitoring DeepSeek API balance
$ pi install npm:@alexanderfortin/pi-deepseek-usage@cynos-ai/engineer
Cynos — an autonomous AI engineering runtime with evidence-based completion verification.
$ pi install npm:@cynos-ai/engineerpi-cache-optimizer
Improve Pi prompt/KV cache hit rates with stable prompts, OpenAI-compatible cache keys, proxy compat warnings, and footer cache stats.
$ pi install npm:pi-cache-optimizerpi-loop-police
Pi extension: detects and interrupts infinite thinking-block and tool-call loops in real time before they exhaust your context window.
$ pi install npm:pi-loop-policepi-clinepass-provider
ClinePass provider for pi — access GLM-5.2, Kimi K2.7, DeepSeek V4 and more open-weight coding models through Cline's $9.99/mo subscription
$ pi install npm:pi-clinepass-provider@rohaquinlop/pi-deepseek-cache
DeepSeek prefix cache optimization for pi — date/CWD freeze, hit-rate telemetry, cache-friendly compaction, and TUI overlays
$ pi install npm:@rohaquinlop/pi-deepseek-cachepi-search-tools
LLM-driven web search and content extraction extension for Pi — Tavily, Exa, Anysearch, Gemini, DeepSeek, Jina, and Firecrawl.
$ pi install npm:pi-search-tools@beyona/pi-zai-usage
Pi extension for monitoring Z.ai, DeepSeek, and OpenAI Codex usage
$ pi install npm:@beyona/pi-zai-usagepi-tool-repair
Validate-then-repair extension for pi — fixes common LLM tool-call mistakes (null fields, stringified arrays, wrong field names, anchor bleed) before tools execute
$ pi install npm:pi-tool-repairpi-opencode-go-cache
Prompt caching for Pi's OpenCode Go provider (kimi, deepseek, mimo, qwen, minimax). Stamps prompt_cache_key, 24h retention, and cache_control breakpoints on every request — beyond what pi-ai or opencode CLI do by default.
$ pi install npm:pi-opencode-go-cache@liziy/token-stats
pi 的 Token 用量与配额监控扩展 —— Footer 实时显示 5h/周 配额剩余、缓存命中率、输出速率，跑到一半不再被限流中断；JSONL 记录 + /stats 日/小时/周/月多维查询
$ pi install npm:@liziy/token-statspi-deepseek-pricing
DeepSeek model pricing extension for pi coding agent — shows peak/off-peak pricing status in the status bar
$ pi install npm:pi-deepseek-pricingpi-alibaba-models
The complete Alibaba provider for pi — Plan subscription + Cloud pay-per-token, International + China endpoints, Anthropic + OpenAI shapes, native thinking levels. Qwen 3.7 Max, Qwen 3.7 Plus, Qwen 3.6 Max, Qwen 3.6 Plus, DeepSeek V4 Pro, Kimi K2.6, GLM-5
$ pi install npm:pi-alibaba-modelsfff-subconscious-pi
Background memory for the pi coding agent. Before each LLM call it greps your local text corpora (past session transcripts, notes) with fff, makes one cheap DeepSeek call, and injects a short synthesized insight into the prompt as context.
$ pi install npm:fff-subconscious-pipi-deepseek-optimized
Harness techniques for DeepSeek V4 Pro on the pi coding agent (cache stability, storm-breaker, hashline editing, plan mode, rewind).
$ pi install npm:pi-deepseek-optimizedpi-windsurf
Windsurf/Cognition models in Pi — Claude, GPT, Gemini, Kimi, DeepSeek, SWE via your Windsurf subscription
$ pi install npm:pi-windsurfpi-deepseek-peak-alert
Pi extension that warns you with desktop notifications when using DeepSeek during peak pricing hours (2× rates)
$ pi install npm:pi-deepseek-peak-alertdeepseek-peak-pricing-hours
Pi extension showing DeepSeek API peak pricing hours (Beijing-time windows displayed in your local timezone)
$ pi install npm:deepseek-peak-pricing-hours@senomas/proxy-provider
A [pi-coding-agent](https://github.com/earendil-works/pi-coding-agent) extension that registers a **deepseek** provider via a configurable AI proxy.
$ pi install npm:@senomas/proxy-provider@mcowger/pi-llmgateway
A Pi extension that adds [LLM Gateway](https://llmgateway.io) as a model provider, giving you access to 160+ chat models from OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, and many others through a single OpenAI-compatible API.
$ pi install npm:@mcowger/pi-llmgatewaypi-analyst-worker-orchestrator
Token-aware analyst/worker workflow and token ledger extension for Pi Dev coding agents.
$ pi install npm:pi-analyst-worker-orchestratorpi-ultraplan
Provider-agnostic ultraplan engine for Pi — fan-out planning, adversarial verification, structured plans, worktree-isolated execution. Reference adapter: fairy-tales-deepseek-openai / deepseek-v4-pro.
$ pi install npm:pi-ultraplanpi-windsurf-beta
Windsurf/Cognition models in Pi — Claude, GPT, Gemini, Kimi, DeepSeek, SWE via your Windsurf subscription
$ pi install npm:pi-windsurf-betapi-reasonix
DeepSeek-native optimizations for Pi: cache-first prefix stabilization, tool-call repair, and cost control.
$ pi install npm:pi-reasonixpi-volcengine-coding-plan
Pi extension for Volcengine Coding Plan, registering Volcengine as a custom OpenAI-compatible provider for domestic coding models.
$ pi install npm:pi-volcengine-coding-plan@jc4649/pi-autocompact
pi coding-agent extension: proactive auto-compaction with a configurable, cheap summarization model (formerly deepseek-compact)
$ pi install npm:@jc4649/pi-autocompactpi-deepseek-balance-status
Pi extension that shows your DeepSeek account balance in the status bar
$ pi install npm:pi-deepseek-balance-status@fyeeme/pi-statusline
Rich custom status bar for pi with token usage, cost, DeepSeek balance, context window, timing, and MCP connection status.
$ pi install npm:@fyeeme/pi-statuslinepi-byteplus-modelark
Pi extension for BytePlus ModelArk Coding Plan — registers ModelArk as a custom OpenAI-compatible provider with all supported coding models.
$ pi install npm:pi-byteplus-modelarkpi-deepseek-startup
DeepSeek branded startup UI for Pi: whale splash screen, animated whale working indicator, and a matching DeepSeek theme. Bundles the startup-ui adapter, the DeepSeek page, and the DeepSeek theme in one installable package.
$ pi install npm:pi-deepseek-startuppi-deepseek-cache
DeepSeek prefix-cache extension for pi — hit-rate telemetry, prefix guard, and cache-friendly compaction.
$ pi install npm:pi-deepseek-cachepi-sumopod-connector
SumoPod AI models for Pi coding agent - One-command setup for all SumoPod models
$ pi install npm:pi-sumopod-connectorpi-chinese-motivation
Plays motivational music while Chinese-origin models (DeepSeek, MiMo, Kimi, etc.) are thinking — with dynamic volume ramp and bit-crusher distortion that gets worse the longer the model thinks.
$ pi install npm:pi-chinese-motivation