#llm

No repository description published.

Sandbox runtime for AI coding agents. Firecracker microVMs, a single Go binary, snapshot/fork as first-class primitives.

No repository description published.

AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.

Real-time, AI-assisted log triage CLI/TUI in Go. Silent on noise, speaks on signal — scores logs locally and escalates only genuine anomalies to an LLM (local Ollama by default).

Self-hosted completion gate for coding agents: independent verification before done, durable evidence, CLI and local GUI.

26-tool MCP server for web scraping, crawling, deep research & autonomous extraction — clean Markdown & structured JSON for Claude, Cursor & any MCP client. 1,000 free credits, local-Ollama LLM support.

The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.

Semantic code search for coding agents — search by meaning like grep, trace call graphs, find tests & blast radius. 100% local embeddings (ONNX/MLX), MCP server, plugins for Claude Code, OpenCode, Codex & Droid.

jq-like stream processor for semantic matching and extraction

Provider-neutral Go primitives for typed LLM programming

Smart auto-mode for Claude Code. The safe alternative to --dangerously-skip-permissions.

Models.dev platform bridge for Symfony AI

Deterministic execution harness for AI agents — goals in, structured tasks out, verified results back.

🧠 Self-hosted, privacy-first MCP server for long-term AI memory — save, search & summarize Claude/ChatGPT chat history locally. No cloud, no database.

JoyCode API 代理 — 协议翻译成 Anthropic/OpenAI 兼容格式，让 Claude Code 直接调用 JoyCode支持的模型，比如GLM 5.1等

High-throughput, self-hostable LLM router in Go. BYO provider keys, k8s-native, key pooling + batch + usage observability.

Local-first dynamic memory for agents and apps: SQLite source of truth, vector search candidates, hotness, decay, TTL, namespaces, and benchmarks.

No repository description published.

Lint the documentation & metadata quality of VGI (Vector Gateway Interface) data workers — descriptions, column comments, tags, and example queries — with a quality score, per-version baselines, and agent-friendly output.

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

MCP server for persistent AI memory — give any AI assistant long-term recall. Works with Claude, Kiro, Cursor, Windsurf.

Fux records why your code is the way it is — and checks it's still true.

Turn YouTube, websites, and arXiv papers into a structured, reusable corpus of insights, syntheses, and reports.

No repository description published.

burnban — local meter & cap for AI-agent spend (MIT). Meters watch. Burnban acts.

Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

enola - MCP Architectural Snapshot Server and Knowledge Graph

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

Agent wallet, credential vault, and governance layer for autonomous AI agents