Open-source coding harness for autonomous software agents
nikola_mr64990 · x · 2026-07-20
An open-source coding harness built on CrewAI, positioned as an alternative to Claude Code. The post argues that the model is only the “brain,” while the harness provides the “hands” for coding: planning tasks, using tools, remembering context, editing files, running code, and deciding next steps.
The implementation highlights:
- an autonomous agent loop
- file tools used as long-term memory
- planning for long-running tasks
- subagents with isolated context
- sandboxed execution in a disposable VM
- human-in-the-loop approvals
- persistent memory and checkpointing
A video is included to show the system in action.
Related event: Developer Releases Open-Source Coding Harness(2 posts)→
More from coding & agent
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11