#llm

Local CLI for diagnosing OpenAI- and Anthropic-compatible APIs beyond 200 OK with stream lifecycle checks and reproducible redacted reports.

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.

Local inference daemon. One warm model, many consumers.

MCP server for Flux AI image generation and editing via Ace Data Cloud.

Data Prism is an open-source privacy layer for Java/Spring teams putting LLM agents or MCP clients in front of internal APIs holding customer data. It pseudonymises personal data per privacy scope, refuses anything unclassified, and can keep a hash-chained audit trail.

Adaptive fork of Pi coding agent for self-evolving agent harness experiments

Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

Pre-action evidence revalidation for AI agents. Detect stale reasoning before agents write, send, update, or delete.

No repository description published.

Open-source Go agent runtime for autonomous AI systems and multi-agent automation. MCP, RAG, 15+ LLM providers and 60+ built-in tools in a single binary.

Open-source Java/SpringAI/Spring Boot AI enablement/orchestration layer for applications with RAG, governed actions, providers, vector stores, PII, tenant safety, chat memory, and behavior analysis.

为 DeepSeek 前缀缓存定制的终端 Code Agent(纯 Go),缓存命中率 95-99%,命中输入定价为未命中的 1/30。A terminal coding agent optimized for DeepSeek prefix caching — 95-99% cache hit, cache-hit input priced at 1/30th of cache-miss.

MCP server exposing all Helm CLI capabilities via the Model Context Protocol (Helm v3 + v4)

MCP bridge that drives four coding CLIs — Google's Antigravity (agy), OpenAI Codex, GitHub Copilot, and Cursor — as sub-agents inside Claude Code. Text answers, image generation, real repo work, and parallel swarms, on quota you already pay for.

Local-first private AI memory layer / Digital Brain for conversations, documents, decisions, and model-agnostic knowledge.

jeopi — Encode intention. Decode software. The oh-my-pi engine fused with jeo-code's spec-first discipline.

Multi-model code review council — consensus-driven PR reviews

Lightweight HTML-to-Markdown parser for AI agent workflows — Python CLI and API around a fast Go engine, available on PyPI.

Your documents already know the answer. Fux lets you ask them — offline, deterministic, $0, cited.

Record a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

A framework for Forward Deployed Engineers: from problem statement to a deployable AI project — every decision traced to a fact, every fact to a source.

Run AI-generated JavaScript from Python, securely, in a sandbox: real V8 in a supervised, OS-sandboxed worker process (Seatbelt, Landlock, seccomp), with your Python functions as the only way out.

Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的 Claude Code/Codex 期刊技能包，从选题、识别策略到表格规范与审稿回复全流程，助你快速发论文。

Open-source governed-sandbox control plane for any workload — per-run identity, brokered credentials, layered egress, approvals, and an append-only audit. Coding agents are the flagship use. Apache-2.0, self-hosted.

No repository description published.

jaunt, dont code.

AI-native web fetch engine for LLM agents — browser impersonation, semantic DOM pipeline, MCP server. CGO-free Go.

A self-improving reflection / skill-creation agent on LangGraph — the LangStage reference agent