All 305,250 crates, alphabetically

llm-latency-lens-providersProvider adapters for LLM Latency Lens93Apache-2.0API bindingsDevelopment tools::Profiling llm-linkA universal LLM proxy supporting 10 providers (OpenAI, Anthropic, Zhipu, Aliyun, Volcengine, Tencent, Longcat, Moonshot, Minimax,…1,934MITAPI bindingsCommand line utilities llm-llamaAn implementation of LLaMA (Large Language Model Meta AI) for the `llm` ecosystem.24,002MIT OR Apache-2.0 llm-lspLSP server to communicate with LLMs3,317MIT OR Apache-2.0 llm-managerTerminal UI for managing LLMs237GPL-3.0-or-laterCommand line utilitiesVisualization llm-memory-graphGraph-based context-tracking and prompt-lineage database for LLM systems47MIT OR Apache-2.0Database implementationsDevelopment tools llm-message-dedupRemove duplicate or near-duplicate messages from LLM conversation history17MITText processing llm-message-dispatchRoute incoming messages to named handlers based on keyword or prefix rules17MITText processing llm-message-hashStable canonical hash of LLM request/message structures. Recursive key-sorting JSON canonicalization + sha256, with per-provider…19MIT OR Apache-2.0EncodingText processing llm-meter-cliCommand-line client and daemon executables for LLM Meter14MITCommand line utilitiesDevelopment tools llm-meter-coreProvider-neutral domain types and adapter contracts for LLM Meter29MITCommand line utilitiesDevelopment tools llm-meter-daemonLocal-first provider scheduler, Codex collector, and IPC runtime for LLM Meter17MITCommand line utilitiesDevelopment tools llm-meter-provider-openaiOpenAI Platform and ChatGPT subscription adapters for LLM Meter20MITCommand line utilitiesDevelopment tools llm-meter-provider-testkitMock providers and adapter test helpers for LLM Meter14MITCommand line utilitiesDevelopment tools llm-meter-secret-storeNative Keyring-backed credential storage for LLM Meter22MITCommand line utilitiesDevelopment tools llm-meter-storageSQLite storage, migrations, and retention for LLM Meter20MITCommand line utilitiesDevelopment tools llm-minifyshrink files when pasting into LLMs2,671MIT llm-mockDeterministic mock LLM for testing agent pipelines18MITDevelopment tools llm-model-selectorSelect the best LLM model based on task requirements and budget19MITDevelopment tools llm-multi-turn-builderFluent builder for LLM multi-turn conversation message lists17MITText processing llm-multimodalMultimodal processing for vision and other modalities46,029Apache-2.0Multimedia::ImagesScience llm-muxMultiplexer for LLMs - route prompts to multiple backends378MIT llm-neoxAn implementation of GPT-NeoX for the `llm` ecosystem.23,008MIT OR Apache-2.0 llm-nogginMulti-model codebase knowledge extraction and querying tool21MIT llm-observatory-collectorOpenTelemetry collector with LLM-specific processors for LLM Observatory43Apache-2.0Development tools::ProfilingWeb programming llm-observatory-coreCore types, traits, and utilities for LLM Observatory1,583Apache-2.0Development tools::ProfilingWeb programming llm-observatory-providersLLM provider implementations and pricing models for LLM Observatory335Apache-2.0Development tools::ProfilingWeb programming llm-observatory-sdkRust SDK for LLM Observatory with trait-based instrumentation42Apache-2.0Development tools::ProfilingWeb programming llm-observatory-storageStorage layer for LLM Observatory - handles persistence of traces, metrics, and logs40Apache-2.0Development tools::ProfilingWeb programming llm-ollamallm-ollama description.1,647Unlicense OR MIT llm-openaiOpenAI Chat API provider for the llm-cmd toolkit63MITAPI bindingsAsynchronous llm-optimizerProduction-ready main service binary for LLM Auto Optimizer50Apache-2.0 llm-optimizer-actuatorAction execution and system orchestration648Apache-2.0 llm-optimizer-analyzerStatistical analysis and anomaly detection643Apache-2.0 llm-optimizer-apiCore API types and utilities78Apache-2.0 llm-optimizer-api-grpcHigh-performance gRPC API with streaming support203Apache-2.0 llm-optimizer-api-restProduction-ready REST API with OpenAPI documentation202Apache-2.0 llm-optimizer-api-testsComprehensive API testing suite51Apache-2.0 llm-optimizer-cliBeautiful CLI tool with 40+ commands56Apache-2.0 llm-optimizer-collectorMetrics and data collection from LLM systems193Apache-2.0 llm-optimizer-configConfiguration management with hot-reload support817Apache-2.0 llm-optimizer-decisionIntelligent decision-making engine646Apache-2.0 llm-optimizer-integrationsExternal service integrations (GitHub, Slack, Jira, Anthropic)327Apache-2.0 llm-optimizer-processorData processing and transformation pipeline618Apache-2.0 llm-optimizer-storageMulti-backend storage layer with PostgreSQL, Redis, and Sled582Apache-2.0 llm-optimizer-typesCore types and data structures for LLM Auto Optimizer1,140Apache-2.0 llm-orchestrator-auditTamper-proof audit logging system for LLM workflows with hash chain integrity80MIT OR Apache-2.0 llm-orchestrator-authAuthentication and authorization for LLM Orchestrator82MIT OR Apache-2.0 llm-orchestrator-cliCLI for LLM Orchestrator52MIT OR Apache-2.0 llm-orchestrator-coreCore workflow orchestration engine for LLM pipelines341MIT OR Apache-2.0 llm-orchestrator-providersLLM provider integrations for LLM Orchestrator481MIT OR Apache-2.0 llm-orchestrator-sdkRust SDK for building LLM workflows programmatically215MIT OR Apache-2.0 llm-orchestrator-secretsSecret management for LLM Orchestrator with Vault, AWS Secrets Manager, and environment variable support208MIT OR Apache-2.0 llm-orchestrator-stateState persistence and recovery for LLM workflow orchestrator206MIT OR Apache-2.0 llm-output-parserProduction-grade parser for extracting structured data from LLM responses. Handles think blocks, markdown fences, malformed JSON,…93MITParsing toolsText processing llm-output-validatorRule-based validator for LLM output strings. Enforce length, regex, JSON, allowed values, or custom predicates.17MIT OR Apache-2.0API bindings llm-pii-redactRegex-based PII redaction for LLM prompts and tool outputs, with reversible placeholders.21MITAPI bindingsText processing llm-pingLLM API latency diagnostic — measures DNS, TCP, TLS, TTFT, and throughput17MIT llm-pipelineReusable node payloads for LLM workflows: prompt templating, Ollama calls, defensive parsing, streaming, and sequential chaining48MITAPI bindingsAsynchronous llm-prefix-matchCheck if LLM output matches expected prefix patterns for accept/reject gating18MITText processing llm-pricingA CLI tool to visualize OpenRouter model pricing in a clean, tabular format1,314MITCommand line utilities llm-prompt-cache-statsTrack Anthropic prompt cache hit rates and savings18MITDevelopment tools llm-provenanceProvider-neutral, canonical context hashing and generation provenance types for LLM applications.19MIT OR Apache-2.0Data structuresEncoding llm-provider-idNormalize and parse LLM provider and model identifiers17MITText processing llm-proxyA little proxy for the LLM API vendors1,484MIT llm-quotaCLI tool to inspect and report LLM usage quota information24Apache-2.0 llm-registry-apiAPI layer for the LLM Registry - REST, GraphQL, and gRPC interfaces for model management183Apache-2.0 OR MITDatabase interfacesWeb programming llm-registry-coreCore domain types and models for the LLM Registry - A secure, production-ready registry for Large Language Models575Apache-2.0 OR MITDatabase interfacesWeb programming llm-registry-dbDatabase layer for the LLM Registry - PostgreSQL integration with migrations and repository patterns448Apache-2.0 OR MITDatabase interfacesWeb programming llm-registry-serverProduction-ready server for the LLM Registry - Complete deployment solution with observability39Apache-2.0 OR MITDatabase interfacesWeb programming llm-registry-serviceBusiness logic and service layer for the LLM Registry - Model management, versioning, and validation321Apache-2.0 OR MITDatabase interfacesWeb programming llm-relayShared types, format conversion, and HTTP client for Anthropic and OpenAI LLM APIs326MIT OR Apache-2.0API bindings llm-repairJSON-repair, markdown-extraction, and tool-call recovery helpers for malformed LLM output625Apache-2.0 OR MITParser implementationsText processing llm-request-logStructured log of LLM API requests with IDs, timing, and token counts17MITDevelopment tools llm-response-cacheIn-memory LRU cache for LLM responses keyed by request hash18MITCaching llm-response-windowSliding window of recent LLM responses for context tracking17MITData structures llm-retryRuntime-agnostic exponential backoff with full jitter for LLM API calls. Built-in retryable-error code lists for Anthropic,…19MIT OR Apache-2.0AsynchronousNetwork programming llm-rsA library, with a command line interface, to exploit Large Language Models3,394GPL-3.0-only llm-samplersToken samplers for large language models125,886MIT llm-sampling-paramsBuilder for LLM sampling parameters (temperature, top_p, top_k, stop sequences)17MITText processing llm-schemaA Rust library for type-safe schema conversion between Rust types and LLM.466MIT llm-schema-apigRPC and REST API definitions for the LLM Schema Registry40Apache-2.0API bindingsWeb programming::HTTP server llm-schema-cliCommand-line interface for managing schemas, lineage, analytics, and migrations37Apache-2.0Command line utilitiesDevelopment tools llm-sdkA simple SDK for OpenAI compatible API.7,943MIT llm-sdk-rsA Rust library that enables the development of applications that can interact with different language models through a unified…1,299MIT llm-secretsWorkload identity for AI agents — prove who you are, access only what you should, for only as long as you need154MITAuthenticationCommand line utilities llm-securityComprehensive LLM security layer to prevent prompt injection and manipulation attacks225MITAuthenticationCryptography llm-sentinelEnterprise-grade anomaly detection and observability platform for LLM applications39Apache-2.0Command line utilitiesDevelopment tools llm-sentinel-alertingRabbitMQ and webhook alerting with deduplication for LLM-Sentinel anomaly detection182Apache-2.0AsynchronousWeb programming llm-sentinel-apiREST API server with health checks, Prometheus metrics, and query endpoints for LLM-Sentinel184Apache-2.0AsynchronousWeb programming llm-sentinel-coreCore types, error handling, and configuration for LLM-Sentinel anomaly detection system788Apache-2.0Development toolsWeb programming llm-sentinel-detectionMulti-algorithm anomaly detection engine (Z-Score, IQR, MAD, CUSUM) for LLM telemetry309Apache-2.0AlgorithmsScience llm-sentinel-ingestionKafka ingestion, OTLP parsing, and telemetry validation for LLM-Sentinel182Apache-2.0AsynchronousWeb programming llm-sentinel-storageInfluxDB time-series storage and multi-layer caching (Moka + Redis) for LLM-Sentinel313Apache-2.0CachingDatabase interfaces llm-shield-anonymizeAnonymization for LLM Shield202MIT OR Apache-2.0 llm-shield-apiProduction-grade REST API for LLM Shield34MIT OR Apache-2.0 llm-shield-cloudCloud abstraction layer for LLM Shield - unified traits for AWS, GCP, and Azure484MIT OR Apache-2.0API bindingsWeb programming llm-shield-cloud-awsAWS cloud integrations for LLM Shield - Secrets Manager, S3, CloudWatch36MIT OR Apache-2.0API bindingsWeb programming llm-shield-cloud-azureAzure cloud integrations for LLM Shield - Key Vault, Blob Storage, Azure Monitor34MIT OR Apache-2.0API bindingsWeb programming llm-shield-cloud-gcpGCP cloud integrations for LLM Shield - Secret Manager, Cloud Storage, Cloud Monitoring34MIT OR Apache-2.0API bindingsWeb programming llm-shield-coreCore types and traits for LLM Shield security toolkit585MIT OR Apache-2.0 llm-shield-modelsML model infrastructure for LLM Shield329MIT OR Apache-2.0 llm-shield-nlpNatural language processing utilities for LLM Shield39MIT OR Apache-2.0 llm-shield-scannersSecurity scanners for LLM Shield toolkit183MIT OR Apache-2.0 llm-shield-secretsSecrets detection and management for LLM Shield34MIT OR Apache-2.0 llm-stackCore traits, types, and tools for the llm-stack SDK551Apache-2.0API bindingsAsynchronous llm-stack-anthropicAnthropic Claude provider for the llm-stack SDK304Apache-2.0API bindingsAsynchronous llm-stack-coreCore traits, types, and tools for the llm-stack SDK54Apache-2.0API bindingsAsynchronous llm-stack-ollamaOllama local model provider for the llm-stack SDK303Apache-2.0API bindingsAsynchronous llm-stack-openaiOpenAI GPT provider for the llm-stack SDK303Apache-2.0API bindingsAsynchronous llm-stop-conditionsComposable stop conditions for LLM agent loops: max iters, USD, tokens, seconds, no-progress, custom.17MITAsynchronousRust patterns llm-stop-token-guardDetect if LLM output was truncated by a stop token or max-tokens limit17MITText processing llm-storeJSONL conversation log storage for the llm-cmd toolkit61MITAsynchronousDatabase interfaces llm-stream-accumulatorAccumulate LLM streaming chunks into a complete response17MITText processing llm-structured-retryRetry LLM calls by injecting previous error as a follow-up user message17MITText processing llm-syncCRDT and vector clock primitives for distributed LLM agent state synchronization22MITConcurrencyData structures llm-test-benchA production-grade CLI for testing and benchmarking LLM applications with support for GPT-5, Claude Opus 4, Gemini 2.5, and 65+…51MIT OR Apache-2.0Command line utilitiesDevelopment tools::Testing llm-test-bench-coreCore library for LLM Test Bench - comprehensive testing framework for Large Language Models with 65+ supported models across 14+…193MIT OR Apache-2.0Command line utilitiesDevelopment tools::Testing llm-test-bench-datasetsDataset management and utilities for LLM Test Bench - load, validate, and manage test datasets327MIT OR Apache-2.0Development tools::TestingScience llm-textA Rust library for processing text for LLM consumption37Apache-2.0Parsing toolsText processing llm-think-tag-stripStrip <thinking>/<think> reasoning blocks from LLM output (Claude, DeepSeek, etc.)19MITText processing llm-tokeiToken usage stats CLI for local coding-agent sessions216MITCommand line utilities llm-token-saver-rsRust crate for reducing LLM token consumption in production applications.26Apache-2.0 llm-token-splitSplit long text into overlapping chunks for LLM context windows17MITText processing llm-tokenizerLLM tokenizer library with caching and chat template support1,057,141Apache-2.0Parsing toolsText processing llm-toolFramework-agnostic Rust tool definitions for LLM agents493Apache-2.0 OR MITAPI bindings llm-tool-macrosProcedural macros for llm-tool (#[llm_tool] attribute)555Apache-2.0 OR MITDevelopment tools::Procedural macro helpers llm-tool-mcpModel Context Protocol (MCP) server integration for llm-tool registries283Apache-2.0 OR MITAPI bindings llm-tool-registryRegistry of available tools with schema for LLM agents17MITDevelopment tools llm-tool-runtimeProvider-agnostic tool contracts, registry, dispatch, and receipt plumbing for llm-pipeline264MITAPI bindingsAsynchronous llm-toolkitA low-level, unopinionated Rust toolkit for the LLM last mile problem.20,578MITParsing toolsText processing llm-toolkit-expertise⚠️ DEPRECATED: Use llm-toolkit::agent::expertise instead. This crate is archived and will not receive updates.586MITText processing llm-toolkit-macrosInternal procedural macros for llm-toolkit.20,012MITDevelopment tools::Procedural macro helpers llm-tools-configfor generating LLM tools configurations for OpenAI, Gemini and more.746MIT llm-transpileHigh-performance LLM context bridge — token-optimized document transpiler704Apache-2.0Command line utilitiesEncoding llm-tuiA Terminal User Interface (TUI) for interacting with Language Learning Models (LLM) using llm-cli1,964MITCommand line utilitiesText processing llm-tui-rsTerminal UI for LLM chat with multi-provider support (Ollama, Claude, Bedrock)173MIT llm-turn-counterCount LLM conversation turns with per-role breakdown and limit enforcement17MITText processing llm-utlConvert code repositories into LLM-friendly prompts with smart chunking and filtering269MITCommand line utilitiesDevelopment tools llm-voice-bridgeLightweight pipeline: text → LLM → VOICEVOX → WAV audio39MITAPI bindingsMultimedia::Audio llm-wasmLLM inference primitives for WebAssembly and edge environments: cache, retry, routing, cost tracking, JSON/Markdown formatters22MITNo standard libraryWebAssembly llm-weaverManage long conversations with any LLM30,146MITAPI bindings llm-web3Powering the Web3 with Rust & LLMs445MIT llm-wikiPlaceholder for the 'llm-wiki' crate.29MIT llm-wiki-engineGit-backed wiki engine with MCP/ACP server — bring your own LLM188MIT OR Apache-2.0Command line utilitiesDevelopment tools llm-wiki-libLLM-powered Wiki SDK — Ingest, Query, and Lint pipelines52MIT OR Apache-2.0Command line utilitiesDatabase interfaces llm_adapterA Rust library for adapting various language model APIs to a unified interface.99,999AGPL-3.0-only llm_api_accessA package to query popular LLMs19,264MIT OR Apache-2.0 llm_clientllm_client: The easiest Rust interface for local LLMs5,532MITAPI bindingsAsynchronous llm_devicesllm_devices: Device management and build system for LLM inference3,784MIT llm_huntera library for forensic research of LLM gguf files and more198MITParsing tools llm_interfacellm_interface: The backend for the llm_client crate3,509MIT llm_jsonRust crate to fix malformed JSON outputs from LLMs71,942MIT llm_modelsllm_models: Load and download LLM models, metadata, and tokenizers5,110MIT llm_models_spiderAuto-updated registry of LLM model capabilities (vision, audio, etc.)79,474MITData structuresWeb programming llm_promptllm_prompt: Low Level Prompt System for API LLMs and local LLMs5,280MIT llm_providersA unified source of truth for LLM providers, models, pricing, and capabilities.5,973MITAPI bindingsScience llm_readabilityReadability library for LLM's built in Rust81,298MITCommand line utilitiesWeb programming llm_routerA high-performance router and load balancer for LLM APIs like ChatGPT725MIT llm_runtimeAbstractions and primitives for building agents and runtimes on top of llm_adapter.51,776AGPL-3.0-only llm_serve将 OpenAI 兼容接口的模型绑定 Tool,MCP,Skills 后发布为新的 OpenAI 兼容 API 服务94Apache-2.0 llm_streamA very simple Rust library to simplify streaming api interaction with LLMs, free from complex async operations and redundant…4,285MIT llm_toolsUnified API for AI.702MITAlgorithmsDevelopment tools llm_usagesA CLI tool to track and visualize LLM token usage from Claude Code across projects61MIT llm_utilsThe best possible text chunker and text splitter and other text tools15,639MITMultimedia::EncodingScience llm_xml_casterAn XML caster for LLM structured output in Rust.24MIT llm_xml_caster_helperHelper crate containing proc-macros for llm_xml_caster.103MIT llmakerMake LL(1) token parser code for Rust.1,630MIT llmanA tool for managing LLM application rules(prompts) ...2,764MIT llmaoLarge Language Model API Ops, an abstraction layer for interfacing with different LLM providers92non-standard llmasjudgeLLM as Judge21LicenseRef-ProprietaryWeb programming llmcChat with LLM in your terminal1,407MIT llmccllmcc brings multi-depth architecture graphs for code understanding and generation.3,996Apache-2.0 llmcc-bindingsllmcc brings multi-depth architecture graphs for code understanding and generation.3,749Apache-2.0 llmcc-bumpaloThread-safe bumpalo wrapper with pre-allocation support. Fork of bumpalo-herd (https://crates.io/crates/bumpalo-herd) with…814Apache-2.0 llmcc-collectNode and edge collection for llmcc graph rendering397Apache-2.0 llmcc-corellmcc brings multi-depth architecture graphs for code understanding and generation.5,706Apache-2.0 llmcc-dotDOT format graph rendering for llmcc289Apache-2.0 llmcc-pythonllmcc: llm context compiler4,199Apache-2.0 llmcc-resolverllmcc brings multi-depth architecture graphs for code understanding and generation.483Apache-2.0 llmcc-rustllmcc brings multi-depth architecture graphs for code understanding and generation.4,456Apache-2.0 llmcc-treellmcc brings multi-depth architecture graphs for code understanding and generation.483Apache-2.0 llmcc-tsTypeScript language support for llmcc290Apache-2.0 llmchainA Rust framework for large language models, inspired by LangChain6,699Apache-2.0 llmclientRust LLM client - Gemini, OpenAI, Claude, Mistral, DeepSeek, Groq49,667MIT OR Apache-2.0API bindingsWeb programming::HTTP client llmctlA CLI tool for testing and validating LLM (Large Language Model) services. Supports multiple providers including OpenAI, Gemini,…119MIT llmctxLLM context builder3,491MIT llmdContext management CLI for agentic development — reads, composes, and serves .llms/ documentation.65MITCommand line utilitiesDevelopment tools llmehA provider-agnostic LLM client abstraction with implementations for Hugging Face, Claude, OpenAI, Gemini, Ollama etc.20Apache-2.0API bindings llmenvUniversal scope-aware environment for AI coding agents507MIT OR Apache-2.0Command line utilitiesConfiguration llmenv-configConfiguration handling for llmenv379MIT OR Apache-2.0 llmenv-gitGit utilities for llmenv393MIT OR Apache-2.0 llmenv-pathsPath resolution utilities for llmenv447MIT OR Apache-2.0 llmenv-utilShared utilities for llmenv382MIT OR Apache-2.0 llmfireA pure-Rust, Vulkan-only LLM inference engine (in development). Name reservation for the in-development project.18AGPL-3.0-or-laterScience llmfire-cliThe CLI for LLMFire, a pure-Rust Vulkan-only LLM inference engine (in development). Name reservation for the in-development…18AGPL-3.0-or-laterScience llmfire-ggufGGUF model loading for LLMFire, a pure-Rust Vulkan-only LLM inference engine (in development). Name reservation for the…18AGPL-3.0-or-laterScience llmfire-kernelsThe compute kernels for LLMFire, a pure-Rust Vulkan-only LLM inference engine (in development). Name reservation for the…18AGPL-3.0-or-laterScience llmfire-vulkanThe Vulkan backend for LLMFire, a pure-Rust Vulkan-only LLM inference engine (in development). Name reservation for the…18AGPL-3.0-or-laterScience llmfitRight-size LLM models to your system hardware. Interactive TUI and CLI to match models against available RAM, CPU, and GPU.16,291MITCommand line utilities