Sandbox

1,068 repos for “llm”Clear

Sort

wenjimods/

timeboxed-execution

wenjimods/timeboxed-executionSkills

Agent workflow for deadline-bound execution with evidence gates

101

symgraph/

BinAssistMCP

symgraph/BinAssistMCPConnectors

Binary Ninja plugin to provide MCP functionality.

open-multi-agent/open-multi-agentFrameworks & SDKs

TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.

6.9k

cyberkaida/

reverse-engineering-assistant

cyberkaida/reverse-engineering-assistantConnectors

MCP server for reverse engineering tasks in Ghidra 👩‍💻

825

huggingface/

funes

huggingface/funesTools

Durable, searchable memory of your past agent sessions.

361

nokonoko1203/

claude-code-settings

nokonoko1203/claude-code-settingsRules & Prompts

Best Practices for Claude Code Configuration

IliaLarchenko/robot_MCPConnectors

A simple MCP server for the SO-ARM100 control

string-os/

string

string-os/stringFrameworks & SDKs

Markdown that runs — one file, any agent.

sabertaz/

notes

sabertaz/notesOther

:bookmark: Personal notes: today I learned

bsquang/

claude-comstyle

bsquang/claude-comstyleSkills

13 prompts to control how Claude communicates — choose your style, cut the noise.

SihyeonJeon/why-was-fable-bannedHooks

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

MemPalace/

mempalace