Library
88,222 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
ComparEdge LLM Cost
MCP serversToken cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
Source for ComparEdge LLM Cost (opens github.com) @comparedge/llm-cost-mcp@1.0.0 -
The Bridge Stack — one stack, every LLM linked
MCP serversOpenAI-compatible BYOK LLM gateway: per-task routing, shadow evaluation, promotion gates.
-
OmniMem
AI repositoriesSelf-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.
Source for OmniMem (opens github.com) git clone https://github.com/richarvey/OmniMem.git -
stocks-llm
MCP serversPlain-English stock search joining congress and insider purchases with SEC fundamentals. Not advice.
-
Cohort
Agents & frameworksLocal-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory.
Source for Cohort (opens github.com) git clone https://github.com/congchuanling-dot/Cohort.git -
foldkit-plus
MCP serversFoldkit Plus: packages for Foldkit apps. Server data (Remote), local-first sync, routing (Site), SSR, forms, CRUD, a CMS, rich text, a page builder, and AI agents over MCP and WebMCP.
Source for foldkit-plus (opens github.com) git clone https://github.com/doeixd/foldkit-plus.git -
jev-cli
MCP serversCommand-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.
Source for jev-cli (opens github.com) git clone https://github.com/shaharia-lab/jev-cli.git -
hadron
MCP serversA native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.
Source for hadron (opens github.com) git clone https://github.com/s0lda/hadron.git -
DreamTeam
MCP serversA self-organizing swarm of AI agents with no leader: shared task board, git workspace, agents that write their own MCP tools, and the swarm itself as an MCP server for Claude Code.
Source for DreamTeam (opens github.com) git clone https://github.com/VictorAboba/DreamTeam.git -
graphersal
MCP serversIn-memory graph database and Gremlin traversal engine in Rust: browser playground, CLI, MCP server for AI agents, durable store, Python bindings.
Source for graphersal (opens github.com) git clone https://github.com/graphersal/graphersal.git -
engineering-multi-ai-skills
SkillsGeneral engineering skills and provider-neutral multi-agent collaboration workflows, templates and execution tools.
Source for engineering-multi-ai-skills (opens github.com) git clone https://github.com/TianMingKanae/engineering-multi-ai-skills.git -
skills
SkillsIndependent Agent Skills for repository analysis, planning, implementation, review, delivery, design, and runtime verification.
Source for skills (opens github.com) git clone https://github.com/idaibin/skills.git -
agent-orchestra
Datasets & benchmarksAgents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, ownership, handoff, verification, evidence, approval, recovery) enforced in code, plus a reproducible conformance benchmark. Apache-2.0 code, CC BY 4.0 specification, zero dependencies, Node 18+.
Source for agent-orchestra (opens github.com) git clone https://github.com/3338902669-ops/agent-orchestra.git -
statlyte — live LLM pricing
MCP serversLive LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
Source for statlyte — live LLM pricing (opens github.com) statlyte@0.1.1 -
llms-generator-mcp
MCP serversCrawls any website and generates a standards-compliant /llms.txt file and JSON-LD schema bundle.
-
llms.txt Readiness
MCP serversDoes a site publish llms.txt, robots permissions and a sitemap agents can use? Bounded check.
-
Query empirical frontier LLM release velocity, inference token deflation, and enterprise AI spend.
-
easiapiai - LLM API prices
MCP serversLLM API prices by seller: cheapest offer per model, list prices, cost estimates, agent Q&A board.
-
GenPark LLM Token Cost Budget Tracker
MCP serversMulti-model LLM token cost budget ledger and burn rate forecaster enforcing spending limits and earl
Source for GenPark LLM Token Cost Budget Tracker (opens github.com) https://github.com/Alpha-Park/genpark-llm-token-cost-budget-tracker-skill/releases/download/v1.0.1/genpark-llm-token-cost-budget-tracker-skill-v1.0.1.mcpb -
LLM Red-Team Scanner
MCP serversLLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails
-
Local llm serving setup — Atom
MCP serversLocal LLM serving setup audit: a deliverable delivered per API call as an independent atom service.
-
responsible-prompting-api
PromptsResponsible Prompting is an LLM-agnostic tool that aims at dynamically supporting users in crafting prompts that embed responsible intentions and help avoid harmful, adversarial prompts.
Source for responsible-prompting-api (opens github.com) git clone https://github.com/IBM/responsible-prompting-api.git -
svelte-llm-mcp
MCP serversAn MCP server that provides access to Svelte 5 and SvelteKit documentation
-
ask-llm
MCP serversUnified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity
Source for ask-llm (opens github.com) @ask-llm/mcp@1.6.3
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.