InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. text generation model by reflection

    Stale Hugging Face Hub, reflection 34 ♥apache-2.0Updated 25 days ago

    reflection/Beam-1.0-501B-A23B-FP8
  2. headroom-desktop

    Tools & apps

    Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%

    Indexed GitHub, gglucass 647 ★MITUpdated today

    git clone https://github.com/gglucass/headroom-desktop.git
  3. hewn-forge

    Prompts

    HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

    Indexed GitHub, kaderkck 116 ★Updated today

    git clone https://github.com/kaderkck/hewn-forge.git
  4. text generation model by XHToken · transformers

    Stale Hugging Face Hub, XHToken 21 ♥apache-2.0Updated 20 days ago

    XHToken/Spark-X2.6-4B-INT8
  5. Rewrite my text with maximal lexicalization (maximum lexical compression): For every phrase, sentence, or paragraph that has an established equivalent term, term of art, or single word, remove it and replace it with…

    Indexed prompts.chat (CC0 prompt collection), omidzamani2@gmail.com CC0-1.0

  6. contexere

    Agents & frameworks

    The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

    Stale GitHub, fajarhide 377 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/fajarhide/contexere.git
  7. You are a bilingual semantic-compression translator. TASK 1. Detect source language (English ↔ Persian). 2. Output a concise translation in the other language. 3. Preserve domain-specific terms that convey meaning more…

    Indexed prompts.chat (CC0 prompt collection), omidzamani2@gmail.com CC0-1.0

  8. Convert and resize static image URLs to WebP, PNG or JPEG for uploads and agent workflows.

    Stale Official MCP Registry, io.github.kriton-dev Updated 13 days ago 1 note

  9. llmtrim

    Prompts

    Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

    Indexed GitHub, fkiene 274 ★MPL-2.0Updated 4 days ago

    git clone https://github.com/fkiene/llmtrim.git
  10. visual document retrieval model by nvidia · vllm

    Stale Hugging Face Hub, nvidia 22 ♥otherUpdated 26 days ago

    nvidia/Nemotron-3.5-Embed-1B-NVFP4
  11. context-diamond

    MCP servers

    Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.

    Stale GitHub, RainCherb 20 ★MITUpdated 24 days ago

    git clone https://github.com/RainCherb/context-diamond.git
  12. image text to text model by nota-ai · transformers

    Stale Hugging Face Hub, nota-ai 20 ♥otherUpdated 10 days ago 1 note

    nota-ai/Kimi-K3.1-Pro-Global-Pruned-30
  13. image text to text model by vllm-project · transformers

    Stale Hugging Face Hub, vllm-project 23 ♥otherUpdated 11 days ago

    vllm-project/Kimi-K3.1-Pro-pruned75
  14. image text to text model by nota-ai · transformers

    Stale Hugging Face Hub, nota-ai 18 ♥otherUpdated 10 days ago 1 note

    nota-ai/Kimi-K3.1-Pro-Global-Pruned-37
  15. autocode

    Skills

    You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.

    Stale GitHub, ilang-ai 104 ★MITUpdated 25 days ago

    git clone https://github.com/ilang-ai/autocode.git
  16. claude-mem

    Skills

    Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

    Indexed GitHub, thedotmack 117.5k ★Apache-2.0Updated today

    git clone https://github.com/thedotmack/claude-mem.git
  17. Compress, resize and convert images with TinyPNG by URL, and check this month's compression count.

    Indexed Official MCP Registry, io.usefulapi Updated 2 days ago 1 note

  18. LAP

    Tools & apps

    Your agents are guessing at APIs. Give them the actual Agent-Native spec. 1500+ API's Ready To-Use skills, Compile any API spec into a lean, agent-native format. 10× smaller. OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman.

    Stale GitHub, Lap-Platform 345 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/Lap-Platform/LAP.git
  19. A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

    Indexed GitHub, pleasedodisturb 123 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/pleasedodisturb/awesome-llm-token-optimization.git
  20. SwiftLM

    AI repositories

    ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

    Indexed GitHub, SharpAI 799 ★MITUpdated today

    git clone https://github.com/SharpAI/SwiftLM.git
  21. DevProjex

    MCP servers

    Turn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.

    Stale GitHub, Avazbek22 41 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/Avazbek22/DevProjex.git
  22. site

    MCP servers

    Compressed Air Servicing: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

    Stale Official MCP Registry, uk.co.compressedairservicing Updated 44 days ago 1 note

  23. LightCompress

    Datasets & benchmarks

    [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

    Stale GitHub, ModelTC 751 ★Apache-2.0Updated 6 months ago

    git clone https://github.com/ModelTC/LightCompress.git
  24. OmniRoute

    Agents & frameworks

    Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors

    Indexed GitHub, cheaper-inference 87.5k ★MITUpdated yesterday

    git clone https://github.com/cheaper-inference/OmniRoute.git

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.