Heavybit Skill
Agent Infrastructure
The runtime substrate for AI agents: the machine an agent runs on, sandboxes and isolation, agent memory and learning, durable execution and harness design, and the performance and cost of running agents. Drawn from practitioners at exe.dev, Daytona, Letta, Glean, and others.
Built from what these operators shared
Agent Infrastructure
Built from thirteen library resources
What a skill is
A skill is a set of working instructions your agent loads when you need it, built from the strategies operators shared in the Heavybit Library. It guides the work and you still do it. Heavybit reads and approves every skill before it ships, and keeps updating skills as new content enters the Library. Skills are plain text, so you or your agent can read any skill in full before acting on it. Your agent decides how to apply a skill, so check its work; if a skill gets something wrong, ask your agent to report it or email platform@heavybit.com.
Connect your agent
- Add the endpoint below to your harness: Claude Code, Codex, Claude, Cursor, ChatGPT, or another that supports MCP.
- Sign in to your Heavybit account with Google or GitHub when your agent asks. It's free, and your first sign-in creates the account.
- Tell your agent what you're working on. It finds the right skill, or you can ask for one by name.
MCP endpointhttps://crucible.heavybit.com/mcp
Built from the Heavybit Library
The operators behind this skill shared what they know in these talks, podcasts, and articles. Every one is free in the Heavybit Library.
- Podcast
Why Agents Need Computers with David Crawshaw
JUN 3, 2026With David Crawshaw
On episode 11 of High Leverage, Joe Ruscio speaks with David Crawshaw about the shift from traditional developer infrastructure to agent-native computing. David traces lessons from founding Tailscale to now building exe.dev around the idea that âagents need aâŠ
High Leverage · Ep. 11
Why Agents Need Computers with David Crawshaw
Listen68 MIN
- Article
Long-Horizon Agents: From Order-Takers to Outcome Owners
JUL 31, 2026With Amir Zohrenejad
Why arenât agents able to successfully execute complex, long-horizon jobs? Heavybit partner Amir Zohrenejad lays out exactly whatâs missing.
Article
Long-Horizon Agents: From Order-Takers to Outcome Owners
Read8 MIN
- Video
The Long-Horizon Stack
OCT 26, 2026With Amir Zohrenejad
Heavybit General Partner Amir Zohrenejad opens DevGuild with the case that long horizon agents now work, citing OpenAI's 10,000-agent, 88-hour run at the Navier-Stokes problem. He then names the five systems that still need to mature before most engineeringâŠ
Video
The Long-Horizon Stack
Watch8 MIN
- Video
Context that Compounds: Memory, Learning + Long-Running Agents
OCT 26, 2026With Josh Bleecher Snyder, Caitlin Colgrove, Tyler Edwards, and Pasha Sadri
Long-running agents generate more context than they can keep in the prompt, so the hard part is deciding what survives. Josh Bleecher Snyder of exe.dev leads Caitlin Colgrove of Hex, Tyler Edwards of Overmind, and Pasha Sadri of Induction through what getsâŠ
Video
Context that Compounds: Memory, Learning + Long-Running Agents
Watch28 MIN