sbhooley / ainativelang
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)
Why this job: topics: multi-agent, agent-orchestration, ai-agents
What it does
- WASM Sandbox. All hands run in a secure WASM sandbox with configurable memory/instruction limits
- Merkle Audit Trail. Token usage is recorded with cryptographic proofs for accountability
- Taint Tracking. Data lineage tracking for sensitive information
- MCP Native. OpenFang uses AINL as a first-class MCP server
- Tauri Sidecar. Desktop apps can embed AINL via OpenFang sidecar
Get started
pipx install 'ainativelang[mcp]' && ainl setup --auto- Maintenance
- Active
- Last commit yesterday
- Stars
- 616
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.8.0
- Released 6 months ago
- Built with
- Python
- 95% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 40% closed
- 3 still open
- Pull requests
- 58 merged
- 10 waiting
- Releases
- 6
- 6 in the last year
More: languages, topics and project record
Languages
- Python 95%
- Shell 2%
- PowerShell 1%
- TypeScript 1%
Topics
- agent-orchestration
- ai-agents
- claude-code
- compiler
- deterministic-execution
- domain-specific-language
- dsl
- langchain-alternative
- llm-orchestration
- mcp
- model-context-protocol
- multi-agent
Project record
- JobAgent frameworks
- StatusListed
- Commits646
- Forks20
- Watching11
- Stars in 28 days-4
- CreatedMar 10, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026