Search
Nex AGI: Nex-N2.5-Mini
nex-agi
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
...moreNex AGI: Nex-N2.5-Pro
nex-agi
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
...moreagentcore-dashboard-metrics
Plug-and-play turn-metrics logging for LangGraph/Strands/CrewAI agents on Bedrock AgentCore, shaped for CloudWatch Logs Insights + Grafana dashboards.
...moreAgent.Xortron-i1-GGUF
mradermacher
AI model: mradermacher/Agent.Xortron-i1-GGUF
MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-i1-GGUF
mradermacher
AI model: mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-i1-GGUF
hill-tooluse-qwen25-3b-postlr1e-6-kl3e-4-1024x1024-seed42-step250-reasoner
sagnikM
AI model: sagnikM/hill-tooluse-qwen25-3b-postlr1e-6-kl3e-4-1024x1024-seed42-step250-reasoner
hill-tooluse-qwen25-3b-postlr1e-6-kl3e-4-1024x1024-seed42-step250-prior
sagnikM
AI model: sagnikM/hill-tooluse-qwen25-3b-postlr1e-6-kl3e-4-1024x1024-seed42-step250-prior
grpo-tooluse-qwen25-3b-lr1e-6-r8-response2048-seed42-step500
sagnikM
AI model: sagnikM/grpo-tooluse-qwen25-3b-lr1e-6-r8-response2048-seed42-step500
hill-tooluse-qwen25-3b-postlr1e-6-kl3e-3-1024x1024-seed42-step250-reasoner
sagnikM
AI model: sagnikM/hill-tooluse-qwen25-3b-postlr1e-6-kl3e-3-1024x1024-seed42-step250-reasoner
hill-tooluse-qwen25-3b-postlr1e-6-kl3e-3-1024x1024-seed42-step250-prior
sagnikM
AI model: sagnikM/hill-tooluse-qwen25-3b-postlr1e-6-kl3e-3-1024x1024-seed42-step250-prior
sdft-tooluse-qwen25-3b-lr1e-5-response2048-seed42-step1800
sagnikM
AI model: sagnikM/sdft-tooluse-qwen25-3b-lr1e-5-response2048-seed42-step1800
hill-tooluse-qwen25-3b-priorlr1e-5-postlr1e-6-kl3e-4-1024x1024-seed42-step250-reasoner
sagnikM
AI model: sagnikM/hill-tooluse-qwen25-3b-priorlr1e-5-postlr1e-6-kl3e-4-1024x1024-seed42-step250-reasoner
Siftlight
lightsifter
Context-efficient project search and bounded code analysis for Claude Code & Codex & Pi & OMP & kimi ....and remote MCP clients, powered by ripgrep with stable cursors, source inspection, and structural evidence.
...moreRETECO
DataScienceUIBK
RETECO: A SemEval-2027 Shared Task on Reasoning-Oriented Retrieval
Jev X Kit
Kadihx
Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Claude Code skill.
...moreragleap-tools
Standalone, dependency-light tool implementations (calculator, file ops, datetime, unit conversion, JSON/CSV, text utilities) exposing OpenAI/Gemini-style function-calling schemas. No tool-calling execution loop - wire these into your own LLM tool-calling code, or into ragleap-agents when that ships. BYOK, no vendor lock-in.
...morerouterl-nightly
RouteRL is a multi-agent reinforcement learning framework for urban route choice in urban traffic networks.
Sift Light
lightsifter
Context-efficient project search and bounded code analysis for Claude Code & Codex & Pi & OMP & kimi ....and remote MCP clients, powered by ripgrep with stable cursors, source inspection, and structural evidence.
...more@araskova/cerberus
anvinpshibu
Cerberus — Universal Security Skill Book & Specification Engine for AI Agents by Araskova Labs.
@araskova/cerberus
anvinpshibu
Cerberus — Universal Security Skill Book & Specification Engine for AI Agents by Araskova Labs.