modelhitch
v0.10.0by bobbybacklogs · author: Geno Ventures Labs
Build and operate BYOK, multi-provider AI applications with ModelHitch.
What modelhitch does, in the publisher's words
ModelHitch Agent Plugin
One shared skill package. Four agent surfaces.
This directory is the distributable ModelHitch plugin package. Codex, Cursor, VS Code, and GitHub Copilot select their own manifest while sharing skills/modelhitch/.
- npm and React integration
- BYOK credential storage and precedence
- normalized chat, streaming, and tool loops
- local multi-wire bridge operation
- provider/model routing and custom gateways
- auto-mode failover, usage, and cost telemetry
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 1
- MCP servers
- 0
- Stars
- 0
- License
- MIT
- Repo created
- 2026-08-11
- Last pushed
- 2026-09-30
- Publisher type
- User
- Version
- 0.10.0
Links
Skills · 1
- modelhitch
- Build, integrate, configure, operate, or troubleshoot ModelHitch, the TypeScript BYOK multi-provider AI layer and local agent bridge. Use for ModelHitch npm or React integrations, provider-neutral chat and streaming, tool loops, custom providers, bridge setup for Codex/Claude/Gemini/OpenAI-compatib…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
ai · llm · byok · providers · bridge
Related by publisher and keywords
Verification-first agent operating system powered by OpenCode Zen and OpenCode Go via ModelHitch.
OpenAI-compatible Hitch API tools: list models and chat completions via Bearer auth.
GitLab MCP server exposing up to 1088 self-managed GitLab REST/GraphQL MCP tools, or 1094 on GitLab.com Ultimate with Orbit. Includes a default 2-tool dynamic surface, 34 base / 51 self-managed Ultimate / 52 GitLab.com Ultimate meta-tools, 45 resources, 37 prompts, 18 completion types, and 4 MCP capabilities (completions, progress, elicitation, resource subscriptions).
Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.
Real-time web search, reasoning, and research through Perplexity's API
[](https://agentpluginsdirectory.com/plugins/modelhitch--bobbybacklogs)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.