Reading
VichuFlow is an open-source cross-platform runtime that runs workflows as persistent state machines, coordinates external coding agents, and decides phase transitions based on self-verified evidence, never blindly trusting agents' self-reports.
Section 01
VichuFlow is an open-source cross-platform runtime that runs workflows as persistent state machines, coordinates external coding agents, and decides phase transitions based on self-verified evidence, never blindly trusting agents' self-reports.
Section 02
Section 03
Current AI coding assistants and agents perform well in code generation, but their code correctness verification is worrying. They often claim "Done ✅" and move to the next task, but fail to provide reliable evidence that the code actually works.
Existing tools face a dilemma: either let agents run inside the editor (no external records, can't recover after crashes) or start multiple agents in parallel to show differences (no workflow concept, no verification checkpoints). VichuFlow was born to solve this pain point—it's an external runtime that doesn't trust agents.
Section 04
Each run of VichuFlow is pure text files on disk (state.json + events.ndjson). CLI, TUI, and Web interfaces are just views of these files. This design brings key advantages:
vichu resume commandSection 05
VichuFlow runs commands like tests, code checks, type checks itself, captures exit codes and outputs—only these verification results can authorize phase transitions. If an agent claims success but fails the verification checkpoint, it can't proceed. This "show, don't tell" philosophy ensures code quality.
Section 06
VichuFlow isn't tied to a single agent provider. You can implement features with one agent, review with another—or not use agents at all, just ordinary shell commands. Currently supported adapters include:
Section 07
VichuFlow prevents agents from "lying" through the following means:
Section 08
To prevent agents from damaging work results, VichuFlow provides multi-layer protection:
rm -rf, git push, installation commands before executionKeep going with more reads from the same topic.
Nornir MCP Server is an enterprise-level server based on the Model Context Protocol (MCP). It seamlessly integrates large language models (such as Claude) with the Nornir network automation framework, supporting natural language orchestration for multi-vendor network devices (Cisco, Arista, Juniper, etc.), and providing production-grade features like a dual-engine architecture (NAPALM + Netmiko), intelligent filtering, and a secure sandbox.
Bibliothèque Française LLM is a structured indexing and annotation project for French public domain literature designed specifically for large language models (LLMs). It integrates multiple authoritative sources such as DraCor, Common Corpus, and Wikisource, providing metadata indexing categorized by genre, author, and era, as well as in-depth annotations for dramatic texts (including characters, lines, stage directions, etc.). Its aim is to enable LLMs to efficiently read and understand classic French literary works.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
libmlxforge is an embeddable MLX large language model (LLM) inference engine designed specifically for Apple Silicon. It provides a unified C ABI interface, supports calls from Node.js, Swift, and Rust, and features continuous batching, streaming output, JSON-constrained structured output, and embedding vector generation.