132,621 packages matching “model-reasoning”
dry-uninstall
v0.3.0 · 3 years ago
Empty npm package to "uninstall" unused transitive dependencies
No known vulnerabilities
@openclaw/meta-provider
v2026.7.1 · 1 month ago
OpenClaw Meta provider plugin.
No known vulnerabilities
prd-plugin
v0.16.62 · 23 days ago
Configurable PRD delivery with deterministic workflows, report-first reasoning guards, duplicate-safe state, executable Substrate integration, focused verification, and traceable evidence.
No known vulnerabilities
@howaboua/pi-auto-reasoning-tool
v0.1.11 · 1 month ago
Pi package that gives agents a change_reasoning tool for adjusting reasoning level when substantial work is likely.
No known vulnerabilities
@diegopetrucci/pi-oracle
v0.1.24 · 15 days ago
An Amp-style oracle extension for pi that consults the strongest reasoning model on your current provider.
No known vulnerabilities
@fre4x/openai
v1.1.8 · 14 days ago
OpenAI MCP server providing multimodal analysis, image generation, and transcription.
No known vulnerabilities
@purista/harness-openai
v2.1.1 · 1 day ago
OpenAI model provider adapter for @purista/harness.
No known vulnerabilities
ministats
v1.1.0 · 2 months ago
Claude Code status line showing model, reasoning effort, context usage bar, and session cost (with optional caveman badge).
No known vulnerabilities
@metaharness/workspace-lens
v0.1.2 · 17 days ago
Jacobian-Lens interpretability primitive for open-weight LLMs (Anthropic 2026-07-06, 'Verbalizable Representations Form a Global Workspace'). Reads the model's functional workspace at inference time — lens_l(h)=unembed(J_l·h) — into workspace tokens, laye
No known vulnerabilities
@deepseek-ai/dsh-llm
v0.0.1-rc.1 · 9 days ago
Provider-neutral LLM service interface for the DeepSeek Harness
No known vulnerabilities
mcp-sequentialthinking-tools
v0.0.5 · 3 months ago
Lightweight MCP sequential thinking scratchpad with optional tool-plan validation
No known vulnerabilities
prosemirror-model
v1.25.11 · 1 month ago
ProseMirror's document model
No known vulnerabilities
@deepseek-ai/dsh-session-reference
v0.0.1-rc.1 · 9 days ago
Cross-session snapshot references and durable untrusted model context (ctx.sessionReferences)
No known vulnerabilities
perplexity-mcp
v0.2.3 · 9 months ago
MCP server providing intelligent search, reasoning, and research capabilities powered by Perplexity's specialized AI models
No known vulnerabilities
@xynogen/pix-data
v0.4.5 · 2 days ago
Pi extension — shared model data layer (models.dev + BenchLM), cached at ~/.cache/pi
No known vulnerabilities
ai-sdk-heal
v0.2.0 · 2 months ago
Heal broken Vercel AI SDK message arrays before they hit the provider. Fixes orphaned tool calls, missing reasoning signatures, invalid tool names, and other provider rejections.
No known vulnerabilities
glm-acp-agent
v1.6.0 · 2 days ago
ACP agent in TypeScript that uses the Zhipu AI GLM series (specifically GLM-5.3 and GLM-4.7) as the reasoning core
No known vulnerabilities
@linxin666/dsh-liangshen
v0.2.5 · 8 hours ago
LiangShen (梁神) agent preset for the dsh web GUI: a two-phase anchored-standard preset — the first model request exposes only the builtin Minimal exact two-tool surface (persistent bash plus str_replace_editor) with no runtime contexts or injected instruct
No known vulnerabilities
@llmgateway/models
v1.261.0 · 13 hours ago
Model and provider definitions for [LLM Gateway](https://llmgateway.io) - the unified API for all LLM providers.
No known vulnerabilities
@arnilo/prism-provider-openrouter
v0.2.9 · 18 hours ago
OpenRouter provider package for Prism.
No known vulnerabilities