llm
unifying multiple LLM backends
bitrouter
LLM API router. CLI + TUI + assembly library.
sema-otel
OpenTelemetry GenAI tracing facade for the Sema runtime
TinyHarness
tinyharness - ai coding harness
zeph-llm
LLM provider abstraction with Ollama, Claude, OpenAI, and Candle backends
siumai-protocol-openai
OpenAI(-like) protocol standard mapping for siumai
cerememory-cli
Command-line interface for Cerememory
siumai-spec
Provider-agnostic specs and data types for siumai
uninews
A universal news scraper for extracting content from various news blogs and news sites
bamboo-llm
LLM provider layer (providers, protocol adapters, streaming, routing, model catalog) for the Bamboo agent framework
blazen-controlplane
Distributed workflow control plane for Blazen — workers connect inbound to a central server
ironclaw
Secure personal AI assistant that protects your data and expands its capabilities on the fly
brainos-cortex
LLM provider abstraction, context assembly, and action dispatch for Brain OS
frontend-analyzer-provider
Konveyor external provider for JS/TS/JSX/TSX and CSS/SCSS analysis
acp-llm-adapter
ACP adapter server that exposes LLM providers (DeepSeek, GLM) as agents to ACP-capable editors
embacle
LLM runner library — wraps 12 AI CLI tools as pluggable LLM providers with agent loop, guardrails, and cost tracking
llm-kit-provider
Provider interface and traits for the LLM Kit - defines the contract for implementing AI model providers
iron-providers
Semantic provider boundary for protocol-oriented LLM providers
clausura-cli
CI-native agent CLI for deterministic pipeline gating
cersei-provider
Provider trait and built-in LLM providers for the Cersei SDK
llmrust
Unified Rust interface for 7 LLM providers (OpenAI, Anthropic, DeepSeek, Google Gemini, Ollama, Moonshot, OpenRouter) with HTTP proxy
llm_api_access
A package to query popular LLMs
punch-kernel
The Ring — central kernel and orchestrator for the Punch Agent Combat System
blazen-local-llm
Shared option + request types for Blazen local LLM backends (candle, mistralrs, llama.cpp) and the controlplane local-model factory seam
punch-runtime
Agent execution engine for the Punch Agent Combat System
punch-arena
The Arena — HTTP API server for the Punch Agent Combat System
cerememory-engine
Orchestrator that assembles all Cerememory stores and engines
oneai-memory
OneAI memory system (short-term, long-term, context compression)
thryd
A light weight, embeded llm request router, with cache
llm_providers
A unified source of truth for LLM providers, models, pricing, and capabilities
shore-llm
LLM provider abstraction and request orchestration for the Silvershore daemon
synaptic-tools
Tool registry and execution: ToolRegistry, SerialToolExecutor, ParallelToolExecutor
codetether-agent
A2A-native AI coding agent for the CodeTether ecosystem
nexus-memory-llm
LLM provider abstraction for Nexus Memory System
xcodeai
Autonomous AI coding agent — zero human intervention, sbox sandboxed, OpenAI-compatible
mailrs-intelligence
LLM-powered email analysis primitives: structured extraction, importance scoring, spam classification, and embeddings — with a pluggable LlmProvider trait and an OpenAI-compatible reference implementation
punch-types
Core types for the Punch Agent Combat System
fprovider
Provider library for the fiddlesticks agent harness framework
punch-cli
CLI binary for Punch — The Agent Combat System
punch-memory
Persistence layer for Punch — SQLite-backed storage for fighters, bouts, memories, and knowledge
punch-channels
Channel adapters for messaging platforms in the Punch Agent Combat System
argus-core
AI code review platform — your coding agent shouldn't grade its own homework
collet
Relentless agentic coding orchestrator with zero-drop agent loops
ask-sh
An AI command line assistant, which is context-aware and multi-turn capable
agentforge-core
Shared types, data models, and error types for AgentForge
sema-llm
LLM provider integrations (Anthropic, OpenAI) for the Sema programming language
peon-runtime
A runtime-agnostic agent execution engine with zero-trust context injection, multimodal messaging, and pluggable LLM providers
anyllm
Low-level, generic LLM provider abstraction for Rust
punch-skills
Skill/move system for the Punch Agent Combat System
zeptoclaw
Ultra-lightweight personal AI assistant
lellm-provider
Provider adapters for LeLLM — OpenAI, Anthropic, and more
synaptic-store
Key-value storage for Synaptic agents: Store trait and InMemoryStore
blazen
Rust-native AI workflow engine with event-driven orchestration
cerememory-adapter-openai
Cerememory LLM adapter for openai
cerememory-adapter-gemini
Cerememory LLM adapter for gemini
punch-gorillas
Autonomous agent (Gorilla) system for the Punch Agent Combat System
agentforge-runner
Agent execution engine: parallel workers, trace capture, retry logic (F-03)
clausura-core
Core library for Clausura — a CI-native agent for deterministic pipeline gating
paip
like cat but through llm
cognate-cli
CLI tool for interacting with LLM providers via Cognate
cerememory-transport-grpc
gRPC transport binding for CMP
simple-agent-type
Core types and traits for SimpleAgents
cerememory-store-semantic
Cerememory semantic store implementation
nexus-memory-embeddings
Embedding service for Nexus Memory System using ONNX Runtime
edgecrab-core
Agent core: conversation loop, prompt builder, context compression, model routing
mockql-core
Core library for GenAI-powered GraphQL response mocking via @mock
ironclad-ai-agent
Secure-by-Design Autonomous AI Agent
cerememory-core
Core types, traits, and CMP protocol definitions for Cerememory
langrust
Unified API for LLM providers
rapidgate
still empty (I'm learning Rust), yet 8 brave souls have already downloaded it — thanks for the encouragement! | A high-performance unified API gateway for multiple LLM providers
synaptic-weaviate
Weaviate vector database integration for Synaptic
synaptic-lancedb
LanceDB embedded vector store for Synaptic — serverless embedded vector database
cerememory-decay
Memory decay engine - forgetting curves and noise accumulation
cerememory-association
Spreading activation engine for cross-modal memory association
synaptic-opensearch
OpenSearch vector store for Synaptic
synaptic-e2b
E2B code execution sandbox for Synaptic
synaptic-jina
Jina AI embeddings and reranker for Synaptic
synaptic-milvus
Milvus vector store for Synaptic
synaptic-huggingface
HuggingFace Inference API integration for Synaptic: Embeddings
synaptic-nomic
Nomic AI embeddings for Synaptic
cerememory-store-working
Cerememory working store implementation
synaptic-slack
Slack message loader for Synaptic
synaptic-voyage
Voyage AI embeddings and reranker for Synaptic
synaptic-confluence
Confluence document loader for Synaptic
astrid-llm
LLM provider abstraction with streaming support for Astrid
oneai-platform-ios
OneAI iOS platform adapter — UIAlertController approval gate via C callback bridge
cerememory-evolution
Cerememory evolution engine
oneai-scheduler
OneAI task scheduling with platform heartbeat
synaptic-langfuse
Langfuse observability integration for Synaptic
polyc-llm
Provider-agnostic LLM trait + wire types for polychrome
ironclaw-memory
Memory backends (in-memory, SQLite, Redis) for the IronClaw AI agent framework
forja
Lightweight AI Agent Engine Core Framework
tldrs
README.md generator powered by LLMs and codebase analysis
llm-kit-openai-compatible
OpenAI-compatible provider implementation for the LLM Kit - supports OpenAI, Azure OpenAI, and compatible APIs
loomweave-llm
Loomweave LLM + embedding provider traits, concrete providers (OpenRouter / Codex CLI / Claude CLI), and the outbound HTTP/CLI transport for summaries and embeddings
ironclaw_common
Shared types, paths, and platform helpers used across the IronClaw workspace
ironclaw-providers
LLM provider implementations (Ollama, Anthropic, OpenAI, Groq) for IronClaw
synaptic-postgres
PostgreSQL integration for Synaptic
cerememory-config
Configuration management for Cerememory (TOML + env)
cerememory-adapter-claude
Cerememory LLM adapter for claude
punch-extensions
MCP templates, credential vault, and WASM plugin sandbox for the Punch Agent Combat System
adaclaw
Lightweight, secure, multi-channel Rust AI Agent Runtime
synaptic-sqltoolkit
SQL database toolkit for Synaptic: ListTables, DescribeTable, ExecuteQuery (read-only)
alpine-ai
A lightweight, low-bulk interface for all major LLM providers
self-llm
Unified chat API for multiple LLM providers
ironclaw-tools
Built-in tool implementations (shell, HTTP, search, datetime) for IronClaw
synaptic-condenser
Context condensation strategies for the Synaptic AI agent framework
aws-sdk-elasticinference
AWS SDK for Amazon Elastic Inference
synaptic-secrets
Secret management and output masking for the Synaptic AI agent framework
blazen-llm
LLM provider abstraction layer for the Blazen workflow engine
synaptic-flashrank
Fast local cross-encoder reranker for Synaptic (BM25-based, zero external dependencies)
url-preview
High-performance URL preview generator for messaging and social media applications
optimus-cli
optimus — meta-skill for LLM/agent tooling (wiki, caveman, aura, graphify)
defect-llm
LLM provider implementations (Anthropic, Bedrock, OpenAI, DeepSeek) for the defect agent
lathe-server
Axum HTTP server for exposing Lathe AI agent pipelines as an API
evolve-dashboard
Local-only web dashboard for Evolve
polyc-llm-vertex
LlmProvider backend over the GCP AI platform REST API (WIF/ADC auth)
cerememory-store-procedural
Cerememory procedural store implementation
llm-openai
OpenAI Chat API provider for the llm-cmd toolkit
ironclaw-agents
Agent patterns (ReAct, Router, Planner, Critic-Actor) for the IronClaw AI agent framework
oneai-skill
OneAI SKILL system with progressive disclosure and lightweight selector
llm-latency-lens-providers
Provider adapters for LLM Latency Lens
synaptic-session
Store-backed session lifecycle management for the Synaptic AI agent framework
mc-provider
LLM provider implementations for magic-code (Anthropic, OpenAI, Gemini)
polyc-llm-openai
LlmProvider backend over the OpenAI-compatible /v1/chat/completions API (Ollama, LM Studio, vLLM, llama.cpp, OpenAI)
agent-io
SDK for building AI agents with multi-provider LLM support
aagt-providers
LLM provider implementations for the AAGT AI Agent framework
defect-agent
Core agent runtime for defect: turn loop, context compaction, tools and session orchestration
punch-desktop
Punch Desktop — native desktop wrapper for the Punch Agent OS
horsie-anthropic
Anthropic LLM provider for horsie
api_log_tracker
API log tracker with multi-provider LLM anomaly analysis, HTTP daemon, and TUI dashboard
simreader
Reader for data files and txt files in Rust
evolve-llm
Minimal LLM client (Anthropic Haiku + Ollama) for occasional challenger generation
siumai-provider-xai
xAI provider implementation for siumai (OpenAI-like protocol)
cerememory-transport-mcp
MCP (Model Context Protocol) transport binding for CMP
punch-wire
P2P networking protocol for the Punch Agent Combat System
cf-gears-mini-chat
mini-chat gear: multi-tenant AI chat
llm-optimizer-decision
Intelligent decision-making engine
synaptic-voice
Voice TTS/STT providers for the Synaptic AI agent framework
cognate-providers
OpenAI, Anthropic, and other LLM provider implementations for Cognate
pomfret
Proxy Of Models For Routing, Evaluation & Telemetry — OpenAI-compatible API, backend routing, and web console
legalis-llm
LLM integration layer for Legalis-RS
nous-judge
Async LLM-as-judge evaluators for Nous — plan quality, adherence, task completion
heartbit-core
agentic framework — agents, tools, LLM providers, memory, evaluation
simple-agents-providers
LLM provider implementations for SimpleAgents
agent-code-lib
Agent engine library: LLM providers, tools, query loop, memory
rsclaw
AI Agent Engine Compatible with OpenClaw
cf-mini-chat
Mini-chat module: multi-tenant AI chat
clawft-core
Core engine for clawft (agent loop, message bus, context management)
meritocrab-llm
LLM evaluator trait and implementations for the Meritocrab reputation system
synaptic-runnables
LCEL composition: Runnable trait, pipe operator, Lambda, Parallel, Branch, Fallbacks
aeonic-providers
LLM provider adapters for Aeonic
mirror
unifying multiple LLM backends
oneai-uniffi
OneAI UniFFI binding definitions for cross-platform foreign-language interfaces
vein-recall
Shared memory system for AI agents and tools
blazen-llm-candle
Local LLM backend for Blazen using candle inference engine
polyc
Polychrome SDK umbrella: re-exports the core polyc-* libraries (edge adapter, wire types, agent loop, and LLM provider) so a consumer can depend on one crate
cognate-axum
Axum web framework integration for Cognate LLM providers
agent-diva-providers
LLM provider integrations for agent-diva
rig-bailian
Rig adapter for BaiLian: integrates the BaiLian AI service with the Rig ecosystem (request/response types, streaming, error handling)
tuillem-tui
Ratatui TUI layer for tuillem
polaris_models
Model provider interface and registry for Polaris
agent-diva-neuron
Single-turn neuron node abstraction for agent-diva
nenjo-sessions
Shared session contracts for Nenjo runtime, worker, and future session services
ai-sdk-provider
Provider specification for AI SDK - trait-based interfaces for AI models
devsper-providers
Distributed AI Swarm Runtime
ai-agents-eval
Evaluation runner for YAML-defined AI agents
blazen-audio-whispercpp
Local speech-to-text backend for Blazen using whisper.cpp
cortexai-providers
LLM provider integrations for Cortex: OpenRouter, OpenAI, Anthropic and more
langgraph-providers
LLM providers integration (OpenAI, Anthropic, etc.) for LangGraph applications in Rust
synaptic-sandbox
Container sandbox for secure code execution — Docker and Apple Container backends
optimus-graphify
Folder to multi-modal knowledge graph (graphify port)
synaptic-callbacks
Callback handlers: RecordingCallback, TracingCallback, CompositeCallback
synaptic-scheduler
Job scheduling (cron + interval) for the Synaptic AI agent framework
synaptic-browser
Browser automation tools for the Synaptic AI agent framework
cerememory-store-common
Shared utilities for Cerememory redb-backed stores
synaptic-models
ProviderBackend abstraction and ChatModel wrappers (Retry, RateLimit, StructuredOutput, BoundTools)
synaptic-metrics
Prometheus metrics exporter for Synaptic agent telemetry
synaptic-fireworks
Fireworks AI integration for Synaptic — ultra-fast open model inference
synaptic-perplexity
Perplexity AI integration for Synaptic — online search-augmented LLM
synaptic-groq
Groq provider for Synaptic: ultra-fast LLM inference via Groq LPU
synaptic-deepseek
DeepSeek provider for Synaptic: ultra-low-cost reasoning models
synaptic-together
Together AI integration for Synaptic
synaptic-xai
xAI Grok integration for Synaptic
llm-kit-xai
xAI (Grok) provider implementation for the LLM Kit - supports chat, image generation, and agentic tools
optimus-llm
Provider-agnostic LLM cascade with retries + budget
llm-kit-groq
Groq provider implementation for the LLM Kit - supports chat and transcription models
devsper-core
Distributed AI Swarm Runtime
optimus-aura
Cross-tool persistent memory + policy + verification (aura port)
nosy-cli
nosy: various contents summarization tool powered by artificial intelligence
llm-kit-openai
OpenAI provider implementation for the LLM Kit
synaptic-retrieval
Document retrieval: BM25, MultiQuery, Ensemble, Compression, SelfQuery, ParentDocument
synaptic-memory
Conversation memory: Buffer, Window, Summary, SummaryBuffer, TokenBuffer strategies
forja-memory
Memory and context storage provider for Forja framework
merlion-llm
LLM providers for Merlion Agent (OpenAI-compatible)
rho-provider
LLM provider implementations for rho (Anthropic, OpenAI)
serdes-ai-providers
Provider abstractions and registry for serdes-ai
synaptic-splitters
Text splitters: Character, Recursive, Markdown, HTML, Language, Token
synaptic-prompts
Prompt templates: ChatPromptTemplate, FewShotChatMessagePromptTemplate
amsterdam
A gateway for observing, routing, and transforming prompts
tuillem-config
YAML configuration parsing for tuillem
synaptic-parsers
Output parsers: String, JSON, Structured, List, Enum — all composable as Runnable
synaptic-vectorstores
Vector store trait with in-memory cosine similarity implementation
synaptic-redis
Redis integration for Synaptic: Store and LlmCache
synaptic-eval
Evaluation: ExactMatch, JsonValidity, Regex, EmbeddingDistance, LLMJudge evaluators
synaptic-embeddings
Embeddings trait with Fake and CacheBacked providers
synaptic-anthropic
Anthropic integration for Synaptic: ChatModel
synaptic-cache
LLM response caching: InMemory, Semantic, CachedChatModel
rivven-llm
LLM provider facade for Rivven — unified API for OpenAI, AWS Bedrock, and more
synaptic-gemini
Google Gemini integration for Synaptic: ChatModel
agentforge-api
REST API server for AgentForge (F-07)
synaptic-ollama
Ollama integration for Synaptic: ChatModel + Embeddings
synaptic-chroma
ChromaDB vector store integration for Synaptic
synaptic-pinecone
Pinecone vector store integration for Synaptic
synaptic-elasticsearch
Elasticsearch vector store integration for Synaptic
synaptic-cohere
Cohere integration for Synaptic: Reranker and DocumentCompressor
optimus-wiki
Persistent LLM-authored wiki — ports and extends wiki-llm
tuillem-plugin
External process plugin host for tuillem
synaptic-sqlite
SQLite integration for Synaptic — cache, checkpointer, store, and vector store
nitpicker-agent
Reusable agentic loop (file/git tools + parallel subagents) extracted from nitpicker
synaptic-tavily
Tavily search tool integration for Synaptic
synaptic-qdrant
Qdrant vector store integration for Synaptic
forja-channel
Multi-platform asynchronous I/O channels for Forja
meritocrab-api
HTTP API handlers and middleware for the Meritocrab reputation system
synaptic-mongodb
MongoDB Atlas Vector Search and graph checkpointer integration for Synaptic
synaptic-loaders
Document loaders: Text, JSON, CSV, Markdown, Directory, Web, Notion, GitHub, YouTube, arXiv
cerememory-store-raw
Cerememory raw journal store implementation
xz-provider
LLM 服务提供者抽象层 — 统一的 LLM 服务提供者接口
yallm-storage
Local JSON conversation/response storage for yallm
yallm-server
HTTP server for yallm LLM API conversion proxy
union_square
A proxy/wire-tap service for making LLM calls and recording everything that happens in a session for later analysis and test-case extraction
tuillem-db
SQLite storage layer for tuillem
tuillem-markdown
Terminal markdown rendering for tuillem
rskit-llm-common
Shared LLM provider parsing and error utilities for rskit
tuillem-provider
LLM provider abstraction for tuillem
llmao
Large Language Model API Ops, an abstraction layer for interfacing with different LLM providers
agentforge-optimizer
Optimizer: mutation strategies to generate candidate agent variants (F-05)
nenjo-models
LLM provider trait and implementations — OpenAI, Anthropic, Gemini, OpenRouter, Ollama, and any OpenAI-compatible API
g3-providers
LLM provider abstractions for G3/GB AI coding agent
gitai-wf
AI-powered toolkit that enhances
Gitworkflow
codewandler-flux-providers
flux's concrete LLM providers — the shared Anthropic Messages protocol core plus the Anthropic, OpenAI, OpenRouter, and Ollama wire codecs/credentials (built on the flux-provider abstraction)
yallm-responses
OpenAI Responses/Conversations support and IR conversions for yallm
paperfoot-engram-llm
Chat LLM providers (OpenRouter) for answer generation and judging
enki-llm
LLM integration for the Enki agent framework
synaptic-pdf
PDF document loader for Synaptic
yallm-config
Layered TOML config loading for yallm
cognis-llm
LLM client and provider abstractions for Cognis: Client, LLMProvider trait, chat options, tool definitions, and streaming. Provider implementations (OpenAI, Anthropic, Google, Ollama, Azure) are feature-gated.
Try searching with DuckDuckGo.