Faros

farol is a free, open-source CLI and GitHub Action for assessing pull-request merge risk and showing where changed code reaches. It statically compares the base and head trees using the TypeScript compiler API, go/types, and Python AST parsing, builds declaration and call graphs, and traces changed declarations to affected pages, API operations, RPC methods, jobs, scripts, and other entry points without executing the analyzed code. It combines reach, diff coverage, lint and security findings, dependency changes, and contract breaks into a 0–100 risk score with fast-track, quick-review, or careful-review guidance, then ranks files and identifies checks for the reviewer. It supports TypeScript/React, JavaScript and TypeScript backends, Go, and Python frameworks and tools, and can produce Markdown comments, JSON, or single-file HTML reports; optional Datadog traffic and error data can add operational context. farol runs locally or in CI with no account or hosted service, never sends analyzed code elsewhere, never blocks or approves merges, and is distributed under the MIT license.

Flowise is a visual, low-code platform for building AI agents and agentic workflows by connecting models, components, and third-party integration nodes through a graphical interface. Its monorepo contains a Node.js backend for API logic, a React frontend, component integrations, and autogenerated Swagger API documentation. It can be installed with npm, run with Docker, deployed self-hosted, or used through Flowise Cloud. The repository is archived and its source code is released under the Apache License 2.0.

Halofy is an open-source governance layer between organizational knowledge and AI agents. It resolves actor identity, roles, namespaces, and source scope on the server; enforces access policies; and records provenance, supersedence, append-only audit history, policy decisions, and signed erasure certificates for reads and writes. The repository exposes governed memory and context operations over MCP and HTTP, including writing, reading, searching, assembling, faulting, statistics, forgetting, policy, sharing, pinning, export, and manifest operations. Postgres with pgvector is the operational authority, while retrieval engines connect through an ACL-scoped read-only driver interface; encrypted, Git-versioned knowledge provides a cold tier, and embedded PGlite is the zero-setup local default. It includes connectors for filesystem, Postgres, Obsidian, and manual CSV import, plus an offline demo and hermetic test lane using deterministic stub components.

AgentFlux is a self-hosted agentic AI platform for building visual workflows and autonomous agents. It connects documents, data sources, language models and executable steps in a browser-based canvas, with 17 preconfigured steps, templates, branching, undo/redo, JSON import/export and agent-generated workflows. Agents can run recurring tasks, reuse saved plans and store documents, observations and instructions in a local knowledge base. Its video-to-workflow feature analyzes overlapping video segments using screen changes, selected frames and timestamped speech, then generates a workflow from the recording; it can ask for clarification when an action or integration is unclear. The Docker release includes the application, interface, FFmpeg and local Whisper-based speech recognition, and can connect to Ollama, LM Studio, vLLM or OpenAI-compatible model endpoints. Workflows, documents, credentials and run logs are stored in a named local volume, while the supplied configuration binds the service to localhost. The application has no login and is intended for single-user operation unless an external access-control layer is added. AgentFlux is released under the Apache License 2.0.

FriendliAI is an inference cloud and API for running frontier open-weight and custom AI models in production, with support for long-context inference, real-time streaming, tool calling, and agent workloads. Its stack combines custom GPU kernels, continuous batching, parallel inference, prefix caching with cache-aware routing, and a GPU-, CPU-, and NVMe-based KV-cache hierarchy for repetitive or long agent inputs. It also uses hybrid speculative decoding that adapts to live traffic, alongside multi-cloud scaling and autoscaling. The service provides model APIs and one-click deployment for models from Hugging Face, as well as deployment support for proprietary or fine-tuned models. FriendliAI advertises 99.99% uptime SLAs and reports performance claims including up to 7x faster output token speed and lower inference costs.