SollanSystems/loop-engineer

emit.open_contract seeds a metrics-dirty RUNLOG placeholder about 3 hours ago

help wanted

0

Executable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.

Python

#agent-loops#agent-orchestration#agentic#agentic-workflows#ai-agents#ai-tools#autonomous-agents#claude-code#developer-tools#false-completion#llm#proof-of-done#python#verification

Foreign-harness gap reports — the inspect scoreboard pipeline about 3 hours ago

help wanted

SollanSystems/loop-engineer

0

Executable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.

Python

#agent-loops#agent-orchestration#agentic#agentic-workflows#ai-agents#ai-tools#autonomous-agents#claude-code#developer-tools#false-completion#llm#proof-of-done#python#verification

Integration recipe: ruflo swarm → acceptance gate about 3 hours ago

help wanted

SollanSystems/loop-engineer

0

Executable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.

Python

#agent-loops#agent-orchestration#agentic#agentic-workflows#ai-agents#ai-tools#autonomous-agents#claude-code#developer-tools#false-completion#llm#proof-of-done#python#verification

Integration recipe: OpenHands run → FCR gate about 3 hours ago

help wanted

SollanSystems/loop-engineer

0

Executable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.

Python

#agent-loops#agent-orchestration#agentic#agentic-workflows#ai-agents#ai-tools#autonomous-agents#claude-code#developer-tools#false-completion#llm#proof-of-done#python#verification

Reconcile emit's iteration-outcome vocabulary with metrics' recognized tokens about 3 hours ago

good first issue

SollanSystems/loop-engineer

0

Executable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.

Python

#agent-loops#agent-orchestration#agentic#agentic-workflows#ai-agents#ai-tools#autonomous-agents#claude-code#developer-tools#false-completion#llm#proof-of-done#python#verification

Label self_eval terminal/repair/eval checks honestly as doc-completeness about 3 hours ago

good first issue

SollanSystems/loop-engineer

0

Executable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.

Python

#agent-loops#agent-orchestration#agentic#agentic-workflows#ai-agents#ai-tools#autonomous-agents#claude-code#developer-tools#false-completion#llm#proof-of-done#python#verification

Trigger-phrase disambiguation batch (3 LOW fixes) about 3 hours ago

good first issue

SollanSystems/loop-engineer

0

Executable operating contracts for AI agent loops: 7 typed terminal states, verification-gated completion, bounded repair, and repo-native state — so a loop proves "done" instead of pretending. Claude Code plugin + portable Python core.

Python

#agent-loops#agent-orchestration#agentic#agentic-workflows#ai-agents#ai-tools#autonomous-agents#claude-code#developer-tools#false-completion#llm#proof-of-done#python#verification

Open Issues Need Help