Explore

Visualize, query, and stream to train on multimodal robotics data.

Skill·Apache-2.0·★ 12k·No key

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, qu

Skill·Apache-2.0·★ 2.4k·No key

Open-source C++17 engine for backtesting and forward execution, with a versioned C ABI; Pine Script v6 runs through code generation. Against TradingView's own trade lists, all 7,989 graded probes (309

in the readmethe ABI fixture guide (the README of the private fixture set `settlement_cpp_abi`) for repeated checks. The first run needs network (the verifier initialises the

Skill·Apache-2.0·★ 189·No key

Anthropic’s Model Context Protocol implementation for Oat++

in the readmelogging to a different stream - ex.: to file by providing custom Logger. ```cpp /* Create MCP server */ oatpp::mcp::Server server; /* Add prompts */ server.addPrompt(std::make_shared

Skill·Apache-2.0·★ 50·No key

mcppls — a C++20/23 modules language server: one set of module semantics on GCC, Clang, MSVC and MinGW, for editors (VS Code, Zed, CLion, Neovim), AI Agents (MCP) and CI

Skill·Apache-2.0·★ 18·No key

Local MCP server exposing the Cloudflare Clef-Flash decision model to AI agents — structured decisions with probability outputs, fully offline via llama.cpp.

in the readmellama.cpp and MLX Two local runtimes behind the same `ClefRuntime` interface: | | `llama-cpp` (default) | `mlx` | |---|---|---| | Platforms | macOS, Linux, Windows | macOS / Apple Silicon only | | Model | GGUF from

Node.js·Apache-2.0·★ 7·No key

Multiplatform system monitoring tool using Cosmopolitan Libc

Skill·Apache-2.0·★ 73·No key

Read-only PostgreSQL MCP server for AI assistants: schema, statistics, plans, locks, replication and PgBouncer, read from the catalog. Never writes, never returns table rows.

in the readmemay set `application_name`, which replaces pg_licht's own `pg-licht-cpp/ `. Where several people or assistants share one database role, a different name

Skill·Apache-2.0·★ 11·No key

AI-Inference-Managed-by-AI: Go binary for managing AI inference on edge devices

Go·Apache-2.0·★ 17·No key

Local-first agentic inference engine in C/C++. Multi-tier model routing, grammar-constrained output, MCP tool servers. Embeddable via C ABI.

Python·Apache-2.0·★ 4·Few stars·No key

Multi-LLM development harness — local-first, test-gated, honest by construction. Requirements→spec→plan→build→review→release with real verification gates; operable by humans, CLI, desktop, or other ag

Go·Apache-2.0·★ 9·No key

MCP server for measured local-LLM benchmarks from the AGmind claim registry — AMD Strix Halo (Ryzen AI Max+ 395) llama.cpp numbers today, NVIDIA DGX Spark on the bench. search_claims, get_claim, list_

Node.js·Apache-2.0·★ 4·Few stars·No key

A coding harness that drives small local models through real work: writing and maintaining code, operating a service stack, reviewing diffs, checking security posture, researching against live sources

Node.js·Apache-2.0·★ 1·Few stars·No key

Local multilingual code analysis and inspection for editors, terminals, and AI agents via CLI, MCP, and LSP.

in the readmecommand`. | | `checks. .languages` | Language IDs: `javascript`, `typescript`, `python`, `java`, `go`, `rust`, `c`, `cpp`. Omit to use the adapter defaults; an empty list is valid for workspace

Node.js·Apache-2.0·Few stars·No key

Benchmark local LLM inference engines (llama.cpp, omlx) on your own hardware with real tokens/sec, not borrowed numbers

Python·Apache-2.0·Few stars·No key

MCP server for covdbg: C++ code coverage on Windows for AI agents. Run tests, find uncovered code, and add targeted tests. No rebuild required.

Skill·Apache-2.0·Few stars·No key

Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.

in the skill textdir: `install-cu - /`. ## Step 4: Run Tests Run the following tests * EXAMPLE_CPP_HELLO_WORLD_TEST * EXAMPLE_PYTHON_HELLO_WORLD_TEST * EXAMPLE_CPP_TENSOR_INTEROP_TEST

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

in the skill textand explicitly mention the GGUF / 4-bit tradeoff when it selects `llama-cpp`. - For SGLang prompts, run with `--runtime sglang` and quote `--mem-fraction-static`, `--max

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Chiasmus is an MCP server that gives language models access to formal verification

in the readmeand `chiasmus_formalize` can run embeddings entirely on-device via node-llama-cpp — e.g. `Qwen3-Embedding-0.6B`. `node-llama-cpp` ships as an `optionalDependency

Node.js·Apache-2.0·★ 214·No key

High-performance medical imaging rendering & segmentation platform — Python Qt + VTK/ITK/CGAL/OpenCASCADE hybrid, native C++ compute engine, 95 algorithms, radiomics, MCP & AI integration

in the readmesearch paths are read from `native.cpp_prefix` in > `~/.medaxis/config.yaml` (or the `MEDAXIS_CPP_PREFIX` env var) — see > Native Build . ### ✅ Verify the installation ```bash uv run pytest

Python·Apache-2.0·★ 4·Few stars·No key