17,102 packages matching “reasoning-harness”
pi-reason-harness
v1.0.9 · 4 days ago
Recursive self-improving reasoning harness for pi — iterate, verify, improve. Builds task-specific reasoning strategies on top of any LLM.
No known vulnerabilities
ejentum-mcp
v0.2.2 · 2 months ago
MCP server exposing the Ejentum reasoning harness as eight tools: four dynamic (`reasoning`, `code`, `anti-deception`, `memory`) plus four adaptive (`adaptive-reasoning`, `adaptive-code`, `adaptive-anti-deception`, `adaptive-memory`) that pre-fit the oper
No known vulnerabilities
@deepseek-ai/dsh-compaction-basic
v0.0.1-rc.3 · 6 days ago
Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness
No known vulnerabilities
n8n-nodes-ejentum
v0.2.1 · 2 months ago
n8n community node for the Ejentum Reasoning Harness. Eight operation modes: four dynamic (reasoning, code, anti-deception, memory) and four adaptive (adaptive-reasoning, adaptive-code, adaptive-anti-deception, adaptive-memory) that pre-fit the operation
No known vulnerabilities
@purista/harness-openai
v2.0.0 · 18 hours ago
OpenAI model provider adapter for @purista/harness.
No known vulnerabilities
@metaharness/harness
v0.2.0 · 16 days ago
Algorithmic Agent Harness (ADR-047) — a deterministic control plane that wraps any model/tool/skill as a replaceable worker: utility-scored decisions, four-gate safety, hash-chained receipts, circuit-breaker recovery, adversarial verification, and a bandi
No known vulnerabilities
@deepseek-ai/dsh-client-ui-theme
v0.0.1-rc.1 · 8 days ago
Theme plugin: ThemeService (light/dark/system preference, prefers-color-scheme resolution, theme/change snapshots; no DOM), --dsw-* token base stylesheets; registers the Appearance settings row
No known vulnerabilities
@strands-agents/sdk
v1.13.0 · 6 days ago
TypeScript SDK for Strands Agents framework
No known vulnerabilities
agentic-flow
v2.1.2 · 20 days ago
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
No known vulnerabilities
cspell-grammar
v10.0.1 · 2 months ago
Grammar parsing support for cspell
No known vulnerabilities
@react-native-harness/metro
v1.4.1 · 14 days ago

No known vulnerabilities
deepthink-js
v2.0.1 · 5 days ago
SOTA NPM module for agentic processes using local or cloud LLMs.
No known vulnerabilities
@react-native-harness/plugins
v1.4.1 · 14 days ago

No known vulnerabilities
react-native-harness
v1.4.1 · 14 days ago

No known vulnerabilities
@react-native-harness/config
v1.4.1 · 14 days ago

No known vulnerabilities
ejentum-langgraph
v0.2.0 · 2 months ago
LangGraph.js / LangChain.js integration for the Ejentum Reasoning Harness. createEjentumTools() returns eight agent-callable tools as an array: four dynamic (reasoning, code, anti-deception, memory) plus four adaptive (adaptive-reasoning, adaptive-code, a
No known vulnerabilities
@react-native-harness/runtime
v1.4.1 · 14 days ago
The core test runtime that executes on React Native devices, providing Jest-compatible APIs (describe, it, expect) and managing test collection, execution, and result reporting in native environments.
No known vulnerabilities
@deepseek-ai/dsh-token-meter
v0.0.1-rc.1 · 8 days ago
Replay-aware token measurement service (ctx.tokenMeter) for the DeepSeek Harness
No known vulnerabilities
@ai-sdk/harness
v1.0.75 · 6 hours ago
_This package is **experimental**._
No known vulnerabilities
@rudderhq/cli
v0.7.10 · 12 hours ago
Rudder CLI — orchestrate AI agent teams to run a business
No known vulnerabilities