Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
kit-memory-demo
MCP serversContinuity for agents: a live memory you can read and cite right now, outliving the context window.
-
statlyte — live LLM pricing
MCP serversLive LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
statlyte@0.1.1 -
MCP.SV — El Salvador Knowledge Server
MCP serversDrop El Salvador into your context window: ~280 official ES/EN docs, hybrid search. Free PAT.
-
paritok-4b-v1
Tools & appsNon-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
git clone https://github.com/Paritok-official/paritok-4b-v1.git -
aigent-os
SkillsClaude Code harness and alternative to context compaction: at 80% context it writes a verified capsule, runs /clear and resumes with persistent memory in git. Long-running and multi-agent Claude Code sessions, auto clear instead of auto-compact. MIT, local, Node 18+. Codex adapter.
git clone https://github.com/wrg32786/aigent-os.git -
Cohere: Command A
ModelsCommand A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...
cohere/command-a -
Writer: Palmyra X5
ModelsPalmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...
writer/palmyra-x5 -
Cohere: Command A+
ModelsCommand A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...
cohere/command-a-plus -
Google: Gemma 3 4B
ModelsGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
google/gemma-3-4b-it -
Google: Gemma 3 12B
ModelsGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
google/gemma-3-12b-it -
Google: Gemma 3 27B
ModelsGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
google/gemma-3-27b-it -
seekstone
MCP serversThe Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~26 ms local semantic search, ~2 KB payloads, 25 tools.
git clone https://github.com/shaqmughal/seekstone.git -
Mistral: Mistral Large 4
ModelsMistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...
mistralai/mistral-large-4-0 -
Upstage: Solar Pro 4
ModelsSolar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...
upstage/solar-pro4 -
Upstage: Solar Mini 4
ModelsSolar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...
upstage/solar-mini4 -
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
deepseek/deepseek-v4-flash -
ByteDance Seed: Seed 1.6
ModelsSeed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.
bytedance-seed/seed-1.6 -
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
deepseek/deepseek-v4-pro -
Qwen: Qwen4 Max
ModelsQwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....
qwen/qwen4-max -
MiniMax: MiniMax M3
ModelsMiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
minimax/minimax-m3 -
Mistral: Devstral 2 2512
ModelsDevstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
mistralai/devstral-2512 -
Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...
inclusionai/ling-3.2-flash:free -
Qwen: Qwen3.6 Flash
ModelsQwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...
qwen/qwen3.6-flash -
Google: Gemma 4 31B
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.