Runtime and conversations
Agent execution, durable streaming, bounded history, automatic context compaction, delegation, retries, token caps, tracing, and cooperative cancellation.
Read runtime architectureSee what is available now, what is being built next, and which safety and governance foundations come before higher-risk capabilities.
Public pre-release build. Last reconciled with the public repository on 7 August 2026. Production suitability must be assessed rather than assumed.
The current build provides an end-to-end runtime, context, integration, governance, file, artifact, scheduling, and audit path for governed agents.
Agent execution, durable streaming, bounded history, automatic context compaction, delegation, retries, token caps, tracing, and cooperative cancellation.
Read runtime architectureWorkspace identity, roles, invitations, TOTP and OAuth sign-in, approval controls, schedules, audit and security views, side-effect envelopes, and behavioural evaluations.
Read governance architectureA typed tool registry, one audited dispatch path, effect and egress declarations, tool catalogue, web search and fetch, and progressively disclosed skills.
Review completed plansPer-workspace cloud-storage boundaries, file revisions and tools, multimodal input, and versioned artifacts with previews, restore, and revocable share links.
Review completed plansThirteen governed tools across Gmail, Google Ads, Airtable, and BigQuery, with discovered resources, multi-target context, typed results, and policy per tool.
Explore the integrationsHybrid document retrieval, provenance-tracked persistent memories, prompt-injection framing, and surfaces to inspect, correct, archive, and purge stored context.
Review completed plansThe repository separates the work currently being designed or built from later capabilities. None of these cards describes functionality available today.
The public repository and release workflow exist, but v0.1.0 has not been tagged or published. Launch bookkeeping and the maintainer-controlled release gate remain open.
Open the roadmapThe next harness lane lets a model compose existing governed tools inside a constrained script while preserving validation, audit, approvals, and resumable execution.
Open the roadmapThe applications programme is being re-baselined around versioned packages, workspace installations, explicit resource bindings, and the same identity and dispatch boundaries as the rest of Praxis.
Open the roadmapProduction currently requires cloud storage and a cloud secret manager. Public cloud deployment guides, email transport, and self-service password recovery remain incomplete.
Open the roadmapProvider-native code execution is a separate planned capability from Code Mode. Until its isolation and egress probes land, agents use the typed tools already exposed to them.
Open the roadmapModel failover and durable stream replay remain planned. Today a provider failure ends the run, while durable jobs, schedules, approvals, completion evidence, and audit records preserve the surrounding operational state.
Open the roadmapIntegrations, memory, retrieval, and external actions only move forward when the controls around them are ready.
Operational governance must exist before integrations ship tools that can spend money or change external systems.
Skills, files, integrations, knowledge, and memory must compose through one budgeted prompt-assembly design.
Retrieval, memory, and harness behaviour need scenarios and expected outcomes before optimisation changes land.
New content sources require a threat model and adversarial fixtures before their output reaches model context.
Follow completed work, upcoming capabilities, and the technical decisions shaping each phase.