Browse the directory

Free open-source, config-driven LLM fine-tuning framework covering full and parameter-efficient fine-tuning (LoRA, QLoRA), preference tuning (DPO, KTO, ORPO), and reinforcement learning across many model families through declarative YAML configs.

Lightweight open-source serving framework for building custom AI model inference APIs by defining a LitAPI with setup and predict methods, with batching, streaming, multi-GPU autoscaling, OpenAI-compatible endpoints, and support for compound, multimodal, RAG, and agent pipelines.

Open-source status companion for Claude Code and Codex with live local session state, your-turn alerts, usage views, and native macOS and Windows applications.

Source-backed rules for reviewing AI-generated endpoints and data-access code before merge for insecure direct object reference risk, covering per-request object-level authorization checks, scoped database lookups, identifier exposure, and consistent enforcement across read, write, and admin operations.

Source-backed rules for reviewing AI-generated code that deserializes data before merge for insecure deserialization risk, covering native serialization formats (pickle, PyYAML, Java Serializable) that can execute arbitrary code on untrusted input, safe data-interchange alternatives, and class allowlisting/integrity checks when native formats can't be avoided.

Source-backed rules for reviewing AI-generated code that binds request parameters to model/entity objects before merge for mass assignment risk, covering allowlist field binding, DTOs that exclude sensitive fields, and the framework-specific autobinding features that make this easy to introduce by default.

Source-backed rules for reviewing AI-generated redirect and forward logic before merge for open redirect risk, covering allowlist-based destination validation, relative-path/indexed-mapping alternatives to raw URLs, and the privilege-escalation and phishing impact of an unvalidated redirect target.

Source-backed rules for reviewing AI-generated code that builds or runs operating-system commands, shell invocations, or subprocesses before merge for command injection and argument injection risk, covering library alternatives to shelling out, array-form process APIs, allowlist input validation, and least-privilege execution.

Source-backed rules for reviewing AI-generated JavaScript/TypeScript code before merge for prototype pollution risk, covering unsafe recursive merge/clone/assign helpers on untrusted input, proto and constructor-prototype key handling, and safer alternatives like Map, Set, and Object.create(null).

Source-backed rules for reviewing AI-generated code that renders untrusted data into HTML, JavaScript, URLs, or CSS before merge for cross-site scripting risk, covering context-correct output encoding, dangerous DOM sinks, HTML sanitization, and Content-Security-Policy as defense in depth.

Open-source semantic cache for LLM applications that stores and reuses model responses through embedding similarity to cut API cost and latency, with modular embedding, vector-store, cache-storage, and eviction components.

Open-source Python framework for building real-time voice and multimodal conversational agents, orchestrating speech-to-text, LLM, text-to-speech, voice activity detection, and transports as a composable pipeline with pluggable providers.

Local-first GoodMemory MCP server for giving Claude durable, scoped memory with SQLite storage, auditable recall, explicit deletion, and opt-in governed writes.

Source-backed KLinePic stdio MCP server for turning broker and exchange fills into annotated post-trade candlestick review charts, with capability discovery and no-charge request preflight before quota-consuming rendering.

Open-source, self-hostable AI engine that runs LLMs, vision, voice, image, and video models on your own hardware behind one API, with drop-in OpenAI, Anthropic, and ElevenLabs API compatibility, composable on-demand backends, and no GPU required.

Chinese product-decision skill that distills the reasoning structure of On Contradiction and On Practice into bottleneck diagnosis, stage-aware prioritization, minimal validation, and evidence-driven strategy updates.

Open-source suite of development tools from Microsoft for building LLM applications end to end — create executable flows that link LLMs, prompts, Python, and tools, trace and debug them, evaluate quality against datasets in CI/CD, and deploy to a serving platform.

Open-source all-in-one AI framework for semantic search, LLM orchestration, and language-model workflows, built around an embeddings database that unions sparse and dense vector indexes, graph networks, and relational databases, with pipelines, workflows, agents, and web and MCP APIs.

Open-source library for fast, memory-efficient fine-tuning, reinforcement learning, and training of open LLMs — train 500+ models up to 2x faster with up to 70% less VRAM and no accuracy loss, with LoRA/QLoRA support and export to GGUF, safetensors, vLLM, and Ollama.

Lightweight, modular open-source Python framework for building agentic AI pipelines from atomic, composable components (agents, tools, context providers), built on Instructor and Pydantic.

Open-source domain-specific language from BoundaryML for writing typed LLM functions with structured inputs and outputs, a VSCode playground, and generated clients you can call from Python, TypeScript, Go, and more.

Open-source AI memory platform that gives agents persistent long-term memory by ingesting data in any format and building a self-hosted knowledge graph, combining vector embeddings, graph reasoning, and ontology generation for meaning-based and relationship-based retrieval.

Open-source, LLM-friendly Python web crawler and scraper that turns web pages into clean, LLM-ready Markdown for RAG, agents, and data pipelines, with an async browser pool, caching, structured extraction, and adaptive deep crawling.

Open-source toolkit from the Docling project for parsing PDF, DOCX, PPTX, XLSX, HTML, images, and more into a unified DoclingDocument, with advanced PDF understanding, OCR, and exports to Markdown and JSON for gen AI and RAG workflows.

Modular open-source Python framework for building AI agents and LLM workflows with structures, tools, memory, drivers, and RAG engines, from Griptape.

Open-source observability platform purpose-built for AI agents, with OpenTelemetry-native tracing, plain-English signals, an evals SDK and CLI, SQL dashboards, dataset annotation, and MCP/CLI access, self-hostable with Apache-2.0 SDKs for Python and TypeScript.

Open-source Python framework from Prefect for structured outputs and agentic AI workflows, with tasks, specialized agents, threads, and extract/cast/classify/generate utilities.

Open-source memory layer for AI agents and assistants that extracts, stores, and retrieves user, session, and agent memories so applications can personalize and remember across interactions, with Python and TypeScript SDKs and pluggable vector, graph, and key-value stores.

Open-source Python library from dottxt for structured LLM generation, guaranteeing outputs that match a JSON schema, Pydantic model, regex, grammar, or multiple-choice set during generation across many model backends.

Open-source AI gateway from Portkey for routing to 1600+ LLMs through one OpenAI-compatible API, with automatic retries, fallbacks, load balancing, conditional routing, guardrails, caching, and observability, self-hostable via npx, Docker, or edge deployments.