Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
NVIDIA: Nemotron 3 Ultra
ModelsNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
nvidia/nemotron-3-ultra-550b-a55b -
StepFun: Step 3.5 Flash
ModelsStep 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
stepfun/step-3.5-flash -
DeepSeek: DeepSeek V3.2
ModelsDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
deepseek/deepseek-v3.2 -
MiniMax: MiniMax M2
ModelsMiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...
minimax/minimax-m2 -
Mistral: Mistral Small 3
ModelsMistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
mistralai/mistral-small-24b-instruct-2501 -
OpenAI: GPT-3.5 Turbo 16k
ModelsThis model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...
openai/gpt-3.5-turbo-16k -
Recursive: Flint (free)
ModelsFlint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...
recursive/flint-v1.0:free -
LiquidAI: LFM3-1.7B
ModelsA compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...
liquid/lfm-3-1.7b -
ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...
baidu/ernie-5.5-flash-preview:free -
claude-code-usage-limits
SkillsClaude Code usage limits, shown to Claude: every reply opens with what the remaining budget fits.
git clone https://github.com/ridelink0/claude-code-usage-limits.git -
reviews
PromptsObjective: Summarize many reviews 1. **Process available reviews** * Note the number of reviews and remember that value as "number_reviews" * Overall rating * Rating distribution if visible * It's possible there aren't…
-
TinkyVision
MCP serversScreen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs.
https://github.com/AgewellEPM/tinky-vision-mcp/releases/download/v0.2.0/tinkyvision-0.2.0-macos-arm64.mcpb -
Arc Control (macOS)
MCP serversArc browser MCP for macOS: agent window, snapshots, DevTools input, guardrails
arc-control-mcp@0.4.0 -
deskbrid
MCP serversLinux automation. 125 MCP tools: windows, input, screenshots, clipboard, print, AT-SPI. 9 DEs.
ghcr.io/coe0718/deskbrid:1.2.0 -
Computer Use
MCP serversAccessibility-first desktop control for any agent: background input, agent pointer, zoom, Chrome.
munim-computer-use@0.1.0 -
postbag
MCP serversLocal Claude Code and Codex sessions on one machine exchange letters through native inputs.
postbag@2.3.0 -
Parsi MCP
MCP serversOffline Persian/Iran tools: Jalali dates, validators, Persian text, price inputs, RTL frontend.
parsi-mcp@0.3.0 -
cloak-browser-mcp
MCP serversPlaywright-compatible MCP server on CloakBrowser stealth Chromium: 86 tools, humanized input.
@devinwangd/cloak-browser-mcp@0.2.0 -
Deskhand
MCP serversSafe KDE Plasma (Wayland) desktop control for AI agents: OCR-checked input, approval panel.
https://github.com/sobelendimm/deskhand/releases/download/v0.5.1/deskhand-mcp.mcpb@0.5.1 -
Logistics API
Public APIsNote: This is a (Limited Release) API available only to select developers approved by business units. The Logistics API resources offer the following capabilities: shipping quote – Consolidates into a list a set of live shipping rates, or quotes, from which you can select a rate to ship a package. shipment – Creates a "shipment" for the selected shipping rate. Call…
-
Hotel Ratings
Public APIsBefore using this API, we recommend you read our Authorization Guide (https://developers.amadeus.com/self-service/apis-docs/guides/authorization-262) for more information on how to generate an access token. Please also be aware that our test environment is based on a subset of the production, this API in test only offers 24 hotels; 10 in London and 14 in New-York. You can find the list in our…
-
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 -
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
nvidia/nemotron-3.5-lightning -
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
deepseek/deepseek-v4-flash-0731
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.