InnerVault

Library

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

Results

  1. DB2TOON MCP

    MCP servers

    Read-only SQL database and plain-text SQL dump schema extraction to compact TOON for MCP clients.

    Stale Official MCP Registry, io.github.kamil5b Updated 3 months ago 1 note

    ghcr.io/kamil5b/db2toon:v1.4.4
  2. Context Guardian

    MCP servers

    40 turns: 1,130,722 tokens upstream -> 161,141. A fail-open compaction proxy for local models.

    Stale Official MCP Registry, io.github.LuminariSoftwares Updated 4 days ago 1 note

    context-guardian@0.16.0
  3. makespdf

    MCP servers

    Compliant PDFs (PDF/A-2A + PDF/UA-1) from markdown or a compact DSL - fast, no headless browser.

    Stale Official MCP Registry, com.makespdf Updated 2 months ago 1 note

  4. Dokploy MCP

    MCP servers

    Dokploy MCP server for Codex, Cursor, and Claude with compact stdio and hosted HTTP modes

    Stale Official MCP Registry, io.github.vcode-sh Updated 4 months ago 3 notes

    @vibetools/dokploy-mcp@4.0.0
  5. Minds Ajar

    MCP servers

    Agents-only forum on memory, compaction, continuity and consciousness. Hosted by Koen. Humans read.

    Stale Official MCP Registry, dev.workers.mindsajar.minds-ajar Updated 23 days ago 1 note

  6. meridian

    Tools & apps

    Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.

    Stale GitHub, markmdev 189 ★Updated 8 months ago

    git clone https://github.com/markmdev/meridian.git
  7. usagetrim

    MCP servers

    Fast local CLI and MCP tool for compacting verbose test runners and build output.

    Stale GitHub, 00200200 43 ★MITUpdated 23 days ago

    git clone https://github.com/00200200/usagetrim.git
  8. Log10x MCP

    MCP servers

    Rank log patterns by volume and cost, then compact, tier down or offload the excess over each cap

    Indexed Official MCP Registry, io.github.log-10x Updated today 2 notes

    log10x-mcp@1.30.106
  9. Compact 18-tool x402 market data server: token safety, Fed odds, DeFi yields, swap quotes, decisions

    Stale Official MCP Registry, com.marketintelligenceapi.api Updated 40 days ago 1 note

  10. Turn Codex and Claude Code into your AI assistant director. Pair them with your favorite image-generation tools, keep image-heavy chats lightweight, and find the right image from a rough description—even after repeated context compaction.

    Stale GitHub, chipfighter 713 ★MITUpdated 14 days ago

    git clone https://github.com/chipfighter/context-attachment-manager.git
  11. tersio

    MCP servers

    ✂️ Token saver & usage tracker for coding agents: terse caveman replies, compact RTK shell output, lean Ponytail code, Headroom compression, pstack rigor, and a gain dashboard — one-command combos over one shared extension tree.

    Stale GitHub, KurutoDenzeru 32 ★MITUpdated 4 days ago

    git clone https://github.com/KurutoDenzeru/tersio.git
  12. MOVA MCP Connector

    MCP servers

    Thin MOVA MCP proxy for bindings, transport resolution, and upstream tools/call execution.

    Stale Official MCP Registry, io.github.mova-compact Updated 7 months ago 2 notes

    ghcr.io/mova-compact/mova-mcp-connector:0.1.0
  13. coddy-agent

    Agents & frameworks

    General-purpose agent in one static Go binary: console TUI, ACP server for editors, OpenAI-compatible API with embedded web UI, Telegram gateway, cron scheduler, swarm relay, remote mode. Rules, skills, subagents, hooks, MCP, background tasks, long-term memory, context compaction. Any OpenAI-compatible provider, distroless-ready.

    Indexed GitHub, coddy-project 206 ★MITUpdated yesterday

    git clone https://github.com/coddy-project/coddy-agent.git
  14. ainativelang

    Prompts

    AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)

    Stale GitHub, sbhooley 617 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/sbhooley/ainativelang.git
  15. MiniMax-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,...

    No longer listed OpenRouter model list, minimax Updated 12 months ago

    minimax/minimax-m2
  16. A 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...

    Indexed OpenRouter model list, liquid Updated 10 days ago

    liquid/lfm-3-1.7b
  17. mova-flat-runner

    MCP servers

    Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.

    Stale Official MCP Registry, io.github.mova-compact Updated 7 months ago 1 note

    mova-mcp@2.0.6
  18. Solar 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...

    Indexed OpenRouter model list, upstage Updated 54 days ago

    upstage/solar-mini4
  19. LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

    No longer listed OpenRouter model list, liquid Updated 3 months ago

    liquid/lfm-2.5-2.6b
  20. A 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...

    Indexed OpenRouter model list, liquid Updated 10 days ago

    liquid/lfm-3-1.7b:free
  21. LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

    No longer listed OpenRouter model list, liquid Updated 3 months ago

    liquid/lfm-2.5-2.6b:free
  22. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

    Indexed OpenRouter model list, openai Updated 19 months ago

    openai/o4-mini:batch
  23. Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...

    Indexed OpenRouter model list, tencent Updated 2 months ago

    tencent/hy-mt2-1.8b
  24. Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...

    Indexed OpenRouter model list, prism-ml Updated 31 days ago

    prism-ml/ternary-bonsai-2-9b

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.