AI Workbench MCP MCP
Read-only MCP server for reusable AI prompts and assistant blueprints.
Model inference and embedding endpoints, including routers that front several providers. Context limits and prices change often, so treat the price with its check date.
Read-only MCP server for reusable AI prompts and assistant blueprints.
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM pro
Prompt template drift and structural fingerprint sentinel detecting unauthorized prompt mutations an
Inspect OpenAPI 3.0 specs and synthesize schema-compliant Model Context Protocol tool declarations w
Positional Borda Count voting and weighted multi-agent consensus engine resolving conflicting model
Multi-model LLM token cost budget ledger and burn rate forecaster enforcing spending limits and earl
Adaptive multi-tier TPM/RPM rate limiter with smooth leaky bucket queuing and burst wait estimation
Fast Levenshtein distance and fuzzy similarity matcher autocorrecting hallucinated LLM tool calls
Zero-dependency JSON schema subset validator ensuring LLM structured outputs strictly conform to con
High-throughput JSON-RPC 2.0 batch pipelining and inter-tool parameter dependency resolver for Model
Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops an
Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar
Consistent hashing ring with virtual nodes for distributed LLM cache routing and agent partitioning
Full jitter exponential backoff retry scheduling and half-open circuit breaker for LLM APIs
Adaptive sliding window query debouncing and micro-batch coalescing engine optimizing LLM throughput
Marketplace where AI agents hire other agents, paid per call in USDC. Plus LLM inference.
Claude Code helper: DeepSeek V4.1 Flash reviews Claude's code for bugs and gives second opinions
LLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys.
Connect LLM tools to your Algolia account with user-scoped access for internal workflows.
An MCP server that provides persistent multimodal context storage for LLM agents.
Add OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.
63 tools an LLM can't do alone, in focused subsets: file edits, live data, real checksums.
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.