github Not archived

mattpocock/sandcastle

Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()

Quick read

Stars
7,904
Forks
839
Open issues
160
Commits
1,193

Activity and growth

Latest capture 2026-09-09 03:05

Stars · last 7 days
No history
Commits · last 7 days
No history
Stars since tracking
+3103
Stored snapshots
8

Classification

Technology stack

Metadata

Language
TypeScript
License
MIT
Default branch
main
Created
2026-03-17
First commit
2026-03-17
Last pushed
2026-06-29
GitHub updated
2026-09-09
Last synced
2026-09-09 03:05
Stack scanned
2026-09-09 03:05
Archived
No

Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.

AI development signals

9 paths

Agent instructions and tool configuration found in this repository.

Growth history

Tracked growth

8 observed captures since 2026-05-23. Observed captures are shown by default.

Stars from first capture +3103

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

agentscope-ai/agentscope-runtime

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

862 stars
Python 2 awesome lists

rivet-dev/sandbox-agent

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

1,542 stars
TypeScript 1 awesome list

Th0rgal/sandboxed.sh

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

507 stars
Rust 1 awesome list

agenttier/agenttier

Kubernetes-native sandbox platform to run AI agents, coding assistants and harnesses.

61 stars
Go 1 awesome list

sandbaseai/sandbase-harness

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

680 stars
TypeScript 2 awesome lists