-
-
awesome-hermes-agent Public
Forked from 0xNyk/awesome-hermes-agentA curated list of awesome skills, tools, integrations, and resources for Hermes Agent by Nous Research
Other UpdatedMar 23, 2026 -
awesome-mcp-serverss Public
Forked from fastmcp-me/awesome-mcp-serverssAwesome MCP Servers - A curated list of Model Context Protocol servers
UpdatedMar 23, 2026 -
bigiron Public
Forked from supermodeltools/bigironBig Iron — AI-Native SDLC. Hermes Agent + Supermodel code graph, graph-gated at every phase.
Shell UpdatedMar 19, 2026 -
evals.biz Public
AI evaluation strategy reference library for technical leaders
Nunjucks UpdatedMar 16, 2026 -
mist-go Public
Shared core for the MIST stack. Zero external deps.
-
greynewell Public
My personal README!
-
swe-bench-fast Public
One-command SWE-bench eval harness in Go. Native ARM64 containers with 6.3x test runner speedup on Apple Silicon and AWS Graviton. Pre-built images on Docker Hub.
-
docs Public
Forked from railwayapp/docsRailway documentation
TypeScript MIT License UpdatedMar 3, 2026 -
claude-software-factory Public template
Open an issue. Get a pull request. 6 GitHub Actions workflows that turn any repo into a self-running software factory powered by Claude Code.
-
llm-router-env Public
Gymnasium RL environment for LLM inference routing optimization — cut costs 15-25% vs static strategies
Python MIT License UpdatedMar 2, 2026 -
swe-bench-pro-action Public
GitHub Action for SWE-bench Pro evaluation powered by mcpbr
Shell MIT License UpdatedFeb 26, 2026 -
evaldriven.org Public
Ship evals before you ship features.
-
schemaflux Public
Structured data compiler. Pass pipeline, pluggable backends.
-
mcpbr Public
Forked from supermodeltools/mcpbrModel Context Protocol Benchmark Runner
Python MIT License UpdatedFeb 17, 2026 -
matchspec Public
Eval framework. Define correct, test against it, get results.
-
infermux Public
Route inference across LLM providers. Track cost per request.
-
tokentrace Public
Where did your tokens go? Spans, latency percentiles, alerts.
-
SWE-bench Public
Forked from SWE-bench/SWE-benchSWE-bench: Can Language Models Resolve Real-world Github Issues?
Python MIT License UpdatedFeb 17, 2026 -
agentic-template Public archive
Starter template for AI-first development. Scaffolds AGENTS.md, CLAUDE.md, CHANGELOG, and README so coding agents like Claude Code, Cursor, and Copilot have the right context from day one.
-
mcp-serialization-repro Public archive
Do MCP tools serialize in Claude Code? Empirical study: readOnlyHint controls parallelism, IPC overhead is ~5ms/call. Reproduces #14353.
-
arch-docs Public
Forked from supermodeltools/arch-docsGitHub Action to generate architecture documentation for any repository using Supermodel
JavaScript UpdatedFeb 14, 2026 -
supermodeltools.github.io Public
Forked from GraphTechnologyDevelopers/graphtechnologydevelopers.github.ioGitHub Pages for supermodeltools
Go UpdatedFeb 14, 2026 -
mcp Public
Forked from supermodeltools/mcpSupermodel Model Context Protocol server. Generate code graphs in Cursor, Codex or Claude Code!
TypeScript UpdatedFeb 13, 2026 -
openapi-spec Public
Forked from supermodeltools/openapi-specSpec for Supermodel public API in OpenAPI YAML. Use as a reference or generate your own clients.
UpdatedFeb 13, 2026 -
typescript-sdk Public
Forked from supermodeltools/sdkGenerate useful graphs of your codebase with our TypeScript SDK!
TypeScript UpdatedFeb 13, 2026 -
dead-code-hunter Public
Forked from supermodeltools/auditGitHub Action to find unreachable functions using Supermodel call graphs
TypeScript MIT License UpdatedFeb 11, 2026
{{ message }}