Skip to content
@agentralabs

Agentra Labs

AI/ML Research
README.md

Agentra Labs hero

Open infrastructure for reliable, long-lived AI agents.
Agentra Labs develops open, modular infrastructure for AI agents that need continuity, control, and trust. We focus on persistent state, structured reasoning surfaces, and policy-enforced execution with audit-ready run trails.

Website · AgenticMemory · AgenticVision · AgenticCodebase · AgenticIdentity

Mission

Agentra Labs develops open, modular infrastructure for AI agents that need continuity, control, and trust. We focus on persistent state, structured reasoning surfaces, and policy-enforced execution with audit-ready run trails.
We focus on systems where agents remember, see, understand, and prove with continuity across sessions and environments.

Agentra Labs core pillars

Goals

  • Deliver persistent cognition through graph memory (.amem).
  • Deliver browserless web cartography and action surfaces (.avis).
  • Deliver semantic code intelligence and impact-aware automation (.acb).
  • Deliver cryptographic agent identity with signed receipts and scoped trust (.aid).
  • Keep every sister standalone-first while enabling optional ecosystem integration.

Ecosystem

Agentra Labs ecosystem flow

Collaborate

We are open to:

  • research collaborations
  • OSS contributors and maintainers
  • ecosystem integrations (MCP, desktop agents, infra)
  • sponsorship and institutional partnerships

Contact: hello@agentralabs.tech

Built by Agentra Labs

Popular repositories Loading

  1. agentic-memory agentic-memory Public

    Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

    Rust 8 2

  2. agentic-codebase agentic-codebase Public

    Semantic code intelligence for AI agents — compile repositories into navigable concept graphs with impact analysis, coupling detection, and prophecy.

    Rust 5 3

  3. agentic-contract agentic-contract Public

    Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation tracking, and violation detection. One .acon file. Rust core + MCP server.

    Rust 4 2

  4. agentic-comm agentic-comm Public

    Structured agent-to-agent and agent-to-human communication — channels, pub/sub, message routing, and presence. One .acomm file. Rust core + MCP server.

    Rust 3 1

  5. agentic-vision agentic-vision Public

    Persistent visual memory for AI agents — capture screenshots, embed with CLIP ViT-B/32, compare, recall. MCP server + Rust core library.

    Rust 3 1

  6. xap-protocol xap-protocol Public

    XAP (eXchange Agent Protocol): open economic protocol for autonomous agents.

    Python 3 2

Repositories

Showing 10 of 25 repositories
  • agentic-data Public

    Universal data comprehension for AI agents — infer schemas, track lineage, detect anomalies, transform any format. 122 MCP tools, 16 parsers. Rust core + CLI + MCP server.

    agentralabs/agentic-data’s past year of commit activity
    Rust 0 MIT 0 0 0 Updated Mar 14, 2026
  • agentic-workflow Public

    Universal orchestration engine for AI agents — workflows, pipelines, state machines, batch processing. 24 inventions, 124 MCP tools, .awf format. Rust core + MCP server.

    agentralabs/agentic-workflow’s past year of commit activity
    Rust 0 MIT 0 0 0 Updated Mar 14, 2026
  • agentic-connect Public

    Universal external interface engine for AI agents — 123 MCP tools, 18 protocols, Connection Souls, Intelligent Retry, Encrypted Vault

    agentralabs/agentic-connect’s past year of commit activity
    Rust 0 MIT 0 0 0 Updated Mar 14, 2026
  • xap-sdk Public
    agentralabs/xap-sdk’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Mar 14, 2026
  • hydra Public
    agentralabs/hydra’s past year of commit activity
    Rust 2 MIT 0 0 0 Updated Mar 13, 2026
  • agentralab-tech-web Public

    Documentation site and developer portal for the Agentra ecosystem — five AI agent sisters, one platform.

    agentralabs/agentralab-tech-web’s past year of commit activity
    TypeScript 1 0 0 0 Updated Mar 12, 2026
  • verity-engine Public

    The open-source truth engine for XAP. Deterministic decision provenance and replay.

    agentralabs/verity-engine’s past year of commit activity
    Rust 0 MIT 0 0 0 Updated Mar 10, 2026
  • xap-protocol Public

    XAP (eXchange Agent Protocol): open economic protocol for autonomous agents.

    agentralabs/xap-protocol’s past year of commit activity
    Python 3 MIT 2 6 0 Updated Mar 10, 2026
  • agentic-contract Public

    Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation tracking, and violation detection. One .acon file. Rust core + MCP server.

    agentralabs/agentic-contract’s past year of commit activity
    Rust 4 MIT 2 0 0 Updated Mar 8, 2026
  • agentic-memory Public

    Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

    agentralabs/agentic-memory’s past year of commit activity
    Rust 8 MIT 2 7 0 Updated Mar 8, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.