Open-source model and reasoning effort router for Claude Code and Codex, using Jev or experimental self-hosted Laya.
☆18Oct 22, 2026Updated 3 weeks ago
Alternatives and similar repositories for switchboard
Users that are interested in switchboard are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max …☆17Sep 29, 2026Updated last month
- Extension for the pi agent that allows it to utilise agent shell to call other agentic harnesses as subagents☆12Oct 27, 2026Updated 2 weeks ago
- Local-first, source-cited memory for AI agents☆13Nov 7, 2026Updated last week
- Your WHOOP recovery, sleep, strain and workouts in Claude, ChatGPT or other MCP apps. Self-hosted.☆18Updated this week
- Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by Type…☆13Oct 13, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway☆17Sep 22, 2026Updated last month
- Model-agnostic LLM benchmarking + tuning in one command. A model is a 15-key profile file. Built in production on a 4x NVIDIA DGX Spark c…☆10Sep 16, 2026Updated last month
- A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on Type…☆28Nov 3, 2026Updated last week
- Reliability-first benchmark and evaluation harness for Hermes Agent runtime configurations☆11May 30, 2026Updated 5 months ago
- A Claude Code mod that hands work to Codex, Gemini, Muse and other agent CLIs, and tracks it in one pane.☆19Nov 2, 2026Updated last week
- ☆17Aug 26, 2026Updated 2 months ago
- A Pi agent extension for custom model-based system prompt.☆20Oct 9, 2026Updated last month
- Activity Reflections extension for oh-my-pi: audits recent agent sessions with your active model and surfaces prompt/workflow efficiency …☆14Jul 10, 2026Updated 4 months ago
- A go version of vaping, aimed at dropping in with a smaller footprint and replacing smokeping☆11Apr 5, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Optimized two-node DGX Spark deployment recipe for DeepSeek V4 Flash with vLLM, DSpark, and NVFP4 KV cache☆11Aug 12, 2026Updated 3 months ago
- Autonomous ADS-B Flight Anomaly Detection Engine built with Claude☆14Updated this week
- NestJs module to easily implement event driven architecture using RxJs in any NestJs project☆11Apr 1, 2022Updated 4 years ago
- Interactive subagents running in Herdr panes.☆24Oct 31, 2026Updated 2 weeks ago
- Starter template for Cloudflare Pipelines, which let you ingest real time data streams and load into R2.☆13Apr 23, 2026Updated 6 months ago
- DSpark-style speculative decoding draft head for Qwen3.6-27B AEON: training recipe, paired eval harness, vLLM patches. +11% serve tok/s v…☆14Jul 2, 2026Updated 4 months ago
- ☆11Updated this week
- Claude Code mod: GitHub Flavored Markdown alerts, task lists, strikethrough and Mermaid diagrams in the transcript☆24Oct 5, 2026Updated last month
- Full GLM-5.3 on 4x DGX Spark with kindlingai gr8 (TP4): RigMark prose c1 29.0 -> 40.6 tok/s (+40 %), c4 63.7 -> 76.6☆14Oct 25, 2026Updated 3 weeks ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Give the DeepSeek Harness (dsh) eyes with any text model + any vision model: a vision proxy for chat image attachments and an analyze_ima…☆12Sep 28, 2026Updated last month
- Hikari's curated English measured notes on local LLM systems (serving, specdec, training, steering).☆15Jul 29, 2026Updated 3 months ago
- CLI that benchmarks AI coding agents on OpenCode and shows where the tokens go☆14Oct 16, 2026Updated 3 weeks ago
- Convert React (Native) components for imperative use.☆12Oct 30, 2023Updated 3 years ago
- Uncensored Qwen3.8-27B Ultimate - BF16 master + NVFP4-MIXED deploy. QuickStarts for DGX Spark (one Dynamic DFlash lattice seat @ util 0.8…☆21Updated this week
- Validated vLLM recipe: Qwen3.8-27B-NVFP4 at full 262,144-token context on a single RTX 5090, GPU-only (no CPU offload).☆16Aug 20, 2026Updated 2 months ago
- Self-contained living visual contract for AI agents — drop a .design file (or drag it into chat) and get on-brand UI. OpenAPI for product…☆11Nov 9, 2026Updated last week
- Your coding friend in the terminal.☆27Oct 19, 2026Updated 3 weeks ago
- ☆13Oct 7, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A VSCode extension built on top of steveyegge/Beads that provides a KanBan, Tableview, and record-level add/edit screens☆14Apr 25, 2026Updated 6 months ago
- Build, load, and verify NCCL for switchless DGX Spark RoCE cycles☆21Oct 25, 2026Updated 3 weeks ago
- jambonz session border controller application for outbound calls☆15Oct 23, 2026Updated 3 weeks ago
- A small, nestable agent-loop job primitive: loop(body→until→review) composed with dag, pluggable engines, agent-judge gates, budget + run…☆12Jul 25, 2026Updated 3 months ago
- EXLR8: a DGX Spark tuned quantization format☆14Nov 6, 2026Updated last week
- DEPRECATED legacy mdbase engine, not authoritative. Current implementation: mdbase-dev/mdbase-connect runtime/☆12Updated this week
- Codebase orientation radar for AI agents — instantly understand any file's structure, entry points, exports, configs, and anomalies acros…☆12Aug 18, 2026Updated 2 months ago
Are these results useful?