1,210 tools found
Promptfoo example for OrcaRouter, an OpenAI-compatible adaptive routing gateway to multiple upstream models.
Sub-4-bit quantization plus on-policy distillation recovery for any Hugging Face model - one ModelAdapter per family.
Benchmark for evaluating LLM agents on fixing real-world CVEs inside sandboxed Docker containers, scored against maintainer tests.
Lightweight CLI that filters verbose command output and file content before it reaches your AI agent, cutting token usage.
AI code review CLI from Alibaba that reviews diffs or whole files with line-level precision, using about 1/9 the tokens of general agents.
Formally verified multipolygon intersection algorithm proven correct in Lean 4, with the implementation written autonomously by AI agents.
Open-source Claude Code harness for autonomous vulnerability discovery, verification, and patching of C/C++ memory bugs via ASAN and gVisor sandboxing.
Local-first memory sidecar that builds a persistent knowledge graph from LLM conversations and injects scored context into prompts.
Self-hosted, open-source harness for multi-user, multi-agent teams - config-based access control instead of prompt-based rules.
Self-hosted daemon running Claude Code, Codex, Copilot, OpenCode, and Pi agents in parallel, controllable from phone, desktop, or CLI.
picklesdev is an autonomous agent for end-to-end workflow automation, enabling users to run complete processes without manual intervention.
Agent-based development framework for 1C BSL that configures AI agents like Cursor and Claude Code to work with 1C configurations through modular MCP servers.
