run-llama/llama-agents
58.3
Adequate · 10 November 2026
51.1k
lines of production code
Python
with Go
9
measurements over time
What this system is
Features
Add DBOS durability examples with SQLite and Postgres support
The examples/dbos directory now includes a suite of runnable demonstrations for durable workflow execution using DBOS. These examples cover a quick-start server using SQLite for zero-setup testing, a standalone script demonstrating checkpointing and resume capabilities, a multi-replica setup backed by Postgres (with Docker Compose) for high-availability scenarios, and a demo showing how idle workflows are released from memory and resumed. Users can now explore crash recovery, resumable runs, and multi-replica coordination directly within the examples.
examples/dbos · high confidence
Add Docker Desktop target and local dev infrastructure for Tilt
The Tilt development environment now supports a Docker Desktop target, enabling developers to run the full stack locally with integrated observability and storage. This includes a new Python script to convert environment variables into Kubernetes secrets, Helm values configured for local debugging (hot reload, debug logging), and manifests to deploy a local S3-compatible object store (SeaweedFS) and a Prometheus monitoring instance. A CronJob is also added to prune container images in Kind clusters to prevent storage growth, while a .gitignore rule excludes sensitive secret manifests from version control.
operator/tilt · high confidence
Add Dockerfiles for control plane, app server, operator, and MITM testing
New Dockerfiles have been added to containerize the application's core components and testing infrastructure. The main Dockerfile now supports building and running the control plane (exposing ports 8000 and 8001) and the app server (exposing port 8080), utilizing Python 3.12-slim and the uv package manager. Additionally, a Dockerfile for the Kubernetes operator is provided, building a Go binary from source and packaging it in a distroless image. A separate Dockerfile and entrypoint script are also introduced to simulate corporate MITM proxy scenarios for testing native TLS mode. Also in this area: Security patches for Docker base images and tooling.
docker · high confidence
Add Python client examples for workflow interaction
Added self-contained example scripts in the \examples/client\ directory demonstrating how to use the \llama\_agents.client.WorkflowClient\ to interact with a running \WorkflowServer\. The \base\ subfolder provides a minimal example for submitting runs, streaming events, and retrieving results, while the \human\_in\_the\_loop\ subfolder illustrates handling workflows that pause for human input via \InputRequiredEvent\ and \HumanResponseEvent\.
examples/client · high confidence
Deterministic workflow replay via persistent task journal
The DBOS integration now includes a task journal that records the order of task completions to enable deterministic replay. This feature introduces a \workflow\_journal\ table and CRUD operations for both PostgreSQL (via \asyncpg\) and SQLite, allowing the system to persist and retrieve task keys. During replay, the journal ensures tasks execute in the same order as the original run, and it includes logic to purge stale entries and orphaned operation outputs when transitioning from replay to fresh execution.
_packages/llama-agents-dbos/src/llama\agents/dbos/journal · high confidence
Durable workflow execution with DBOS integration
This change introduces a new DBOS plugin for LlamaIndex Workflows, enabling durable, SQL-backed workflow execution. It adds an ExecutorLeaseManager to handle exclusive executor slot leases via Postgres, allowing dynamic executor identification without pre-defined stable IDs. The integration includes an idle release mechanism that coordinates state transitions (active, releasing, released, resuming) across replicas using a distributed lifecycle lock, ensuring workflows can be safely released when idle and resumed later. Additionally, it centralizes workflow state decoding and serialization, and shares the asyncpg connection pool through a PoolProvider for efficient resource management.
_packages/llama-agents-dbos/src/llama\agents/dbos · high confidence
Initial release of the llama-agents Helm chart
The \llama-agents\ Helm chart (version 0.12.6) is now available, providing a standardized way to deploy the Llama Agents control plane and operator. This chart introduces several key capabilities: an optional \s3proxy\ sidecar for using non-AWS object storage backends, a dedicated \apps.namespace\ setting to isolate \LlamaDeployment\ resources from the operator, and configurable network policies with DNS and private-range blocking. It also includes support for Horizontal Pod Autoscalers (HPA) for both the control plane and operator, and manages CRD version compatibility via a pinned \crds.version\ field.
charts/llama-agents · high confidence
Introduce Bedrock AgentCore integration for workflow execution
This change adds the \llama-agents-agentcore\ package, enabling workflows to run on AWS Bedrock AgentCore. It introduces \AgentCoreService\ and \AgentCoreRuntimeDecorator\ to wrap the standard runtime, ensuring workflows and individual steps are tracked as async tasks within the AgentCore container. The package also includes a CLI entry point (\main.py\) with support for local mode (using a local SQLite store) and production mode, along with utilities to export the necessary entrypoint code for deployment.
packages/llama-agents-agentcore/src · high confidence
Introduce DBOS runtime adapter for durable, distributed workflow execution
This package provides a new DBOS-based runtime adapter for LlamaIndex workflows, enabling durable execution with automatic step recording, replay, and distributed worker support. Key capabilities include per-worker concurrency limits enforced via DBOS queues, an idle-release mechanism that uses 'continue-as-new' to free memory while preserving state, and cross-replica event delivery and streaming through a shared Postgres database. The adapter supports horizontal scaling via executor IDs, handles crash recovery for idle releases, and ensures deterministic replay by seeding retry jitter with the run ID.
packages/llama-agents-dbos · high confidence
Introduce LlamaDeployment and LlamaDeploymentTemplate CRDs with dedicated Helm chart
This change introduces the \LlamaDeployment\ and \LlamaDeploymentTemplate\ Custom Resource Definitions (CRDs) for the llama-agents operator, allowing users to define deployment configurations and pod template overlays via Kubernetes resources. A new \llama-agents-crds\ Helm chart (v0.7.2) is provided to manage the lifecycle of these CRDs, ensuring they are updated during \helm upgrade\ while remaining intact during \helm uninstall\ via the \helm.sh/resource-policy: keep\ annotation. The \LlamaDeployment\ CRD supports fields for specifying repository URLs, git references, container images, and build generation counters to trigger retries, while the \LlamaDeploymentTemplate\ CRD allows users to define default pod spec overlays (e.g., node selectors, tolerations) that merge with operator-computed defaults.
charts/llama-agents-crds, operator/api, operator/cmd · high confidence
Introduce build API, code repo storage, and backup subsystems
The control plane now includes a dedicated FastAPI build API for managing build artifacts (upload, download, existence checks) backed by S3, along with a Git code-repo service that stores bare repositories as tarballs in S3 and serves them via a dulwich-based WSGI layer. A new backup subsystem provides encrypted (.tar.gz) archives of LlamaDeployment CRs and secrets with S3 storage support, including AES-256-GCM encryption and metadata cleaning. These additions introduce new endpoints and internal services for build artifact lifecycle, Git repository persistence, and backup/restore capabilities.
packages/llama-agents-control-plane/src · high confidence
Introduce dev\_cli developer tooling package
Added a new \src/dev\_cli\ package providing a Click-based CLI for developer workflows. This includes a \dev\ entry point that defaults to running pytest, subcommands for managing changesets and publishing, a \sync-skills\ helper, and utilities for updating debugger \index.html\ asset URLs and computing Git tag metadata for GitHub Actions.
_src/dev\cli · high confidence
Introduce llama-agents package structure with server, client, and deployment capabilities
This change establishes the new \llama-agents\ package namespace, replacing the previous \llama-index-workflows\ and \llama-deploy\ naming conventions. It introduces a modular architecture with dedicated packages for the client (\llama-agents-client\), server runtime (\llama-agents-appserver\), and AWS Bedrock AgentCore deployment (\llama-agents-agentcore\). Users can now mount the \WorkflowServer\ as a sub-application in existing FastAPI apps, interact with workflows via a new typed \WorkflowClient\ with event streaming, and deploy workflows to AWS AgentCore using the \AgentCoreDeployer\. The update also includes a new CLI tool (\llamactl\) for managing deployments, backups, and authentication, along with improved observability and serialization support for workflow events.
llama-agents-dev · high confidence
Introduce the Llama Agents App Server for deployment and workflow management
This change adds the \llama-agents-appserver\ package, providing a FastAPI-based application server that serves as the runtime for Llama Agents deployments. It introduces a structured API for managing workflows, including endpoints to create, run, and monitor tasks, as well as stream events and retrieve results. The server supports configurable persistence (memory, local SQLite, or cloud via Agent Data) and offers a UI proxy mode for development environments. It also includes infrastructure for bootstrapping applications from git repositories, building deployment artifacts, and handling graceful shutdowns, effectively establishing the core serving layer for agent deployments.
packages/llama-agents-appserver/src · high confidence
New Docker example for running a WorkflowServer
Added a new Docker example in the \examples/docker\ directory that demonstrates how to containerize and run a \WorkflowServer\. The entry includes a \Dockerfile\ based on Python 3.13 Alpine, a sample \app.py\ defining a \GreetingWorkflow\ with streaming events, and a \README.md\ with build and run instructions. This allows users to easily deploy and test workflow servers in isolated container environments.
examples/docker · high confidence
New Kubernetes + OpenTelemetry example with distributed tracing
Added a self-contained example in \examples/k8s-otel\ that deploys LlamaIndex Workflows on Kubernetes using DBOS for durable execution across two replicas. The setup includes a FastAPI application serving Counter and Greeter (human-in-the-loop) workflows, with distributed tracing exported via OpenTelemetry to Arize Phoenix and Jaeger. It provides a Tiltfile and Kustomize manifests to easily spin up the entire stack (Postgres, Phoenix, Jaeger, OTel Collector) on a local kind cluster.
examples/k8s-otel · high confidence
New dev CLI commands for versioning, publishing, testing, and skills management
The development CLI now includes four new commands to streamline local development workflows. The \changeset-version\ command applies changeset version bumps and synchronizes Python package versions with JavaScript versions, while \changeset-publish\ allows for local planning and publishing of all workspace packages. A new \dev test\ command (pytest\_cmd) runs tests across packages with parallel execution support and displays detailed test counts and failure summaries. Additionally, the \sync-skills\ command symlinks agent skills from the checked-in \.agents/skills\ directory into the \.claude/skills\ directory for use with Claude Code.
_src/dev\cli/commands · high confidence
New example demonstrating resource node visualization in workflow graphs
Added a new example script, \resource\_nodes\_example.py\, that illustrates how to visualize workflow steps dependent on injected resources (such as database, cache, and LLM clients) in both Mermaid and Pyvis formats. This example shows users how resource dependencies are rendered as distinct nodes in the generated workflow diagrams, providing a concrete reference for implementing and debugging resource-aware workflows.
examples/visualization · high confidence
New examples directory with runnable workflow notebooks
The \examples\ directory now contains a curated collection of runnable Jupyter notebooks and code samples demonstrating how to build, serve, and deploy agent workflows using \llama-index-workflows\ and \llama-agents\. The new \README.md\ serves as an index, guiding users through a progression of examples including a feature walkthrough, function-calling agents, document processing pipelines, durable workflows with state persistence, eval-driven prompt refinement, and advanced patterns like streaming internal events and vector database state management.
examples · high confidence
New finance triage agent example
Added a new notebook example in the \examples/document\_agents\ directory that demonstrates a finance team assistant agent. This agent uses LlamaExtract and LlamaClassify to triage incoming emails with attachments (invoices or expenses), extract specific data fields, and simulate appropriate responses based on the classification.
_examples/document\agents · high confidence
New local development environment for the operator
Developers can now spin up a local Kubernetes cluster (kind or Docker Desktop) and run the operator with live-reload via Tilt. This includes a new dev.py CLI script to manage the cluster lifecycle, a Tiltfile that builds and injects the operator and control-plane images, and a Makefile with targets for linting, testing, and Helm chart validation.
operator · high confidence
New observability examples for workflow tracing and logging
The examples/observability directory now includes a README and four new Jupyter notebooks demonstrating how to instrument LlamaIndex workflows. These examples show how to use native LlamaIndex instrumentation with OpenTelemetry to create custom spans and events, how to export traces to third-party platforms like Arize Phoenix and Langfuse, and how to integrate the dispatcher context (including run IDs) into both structlog and standard library logging for structured, correlated log output.
examples/observability · high confidence
New persistent workflow stores for Postgres and LlamaCloud Agent Data
The server now supports persistent workflow state storage via two new backends: a Postgres implementation using asyncpg with LISTEN/NOTIFY for real-time event streaming, and a LlamaCloud Agent Data API client with automatic retries for transient read failures. State is now keyed by both run ID and namespace, allowing multiple state records per run, and the system includes SQL migration utilities to manage schema versions automatically.
_packages/llama-agents-server/src/llama\_agents/server/\store · high confidence
New scripts for manifest processing and documentation synchronization
Added \scripts/process\_manifests.py\ to automate the generation of Helm templates from kubebuilder outputs, specifically handling RBAC rules (splitting leader-election leases into the release namespace when apps and release namespaces differ) and copying CRD files to the appropriate chart directories. Also added \scripts/sync-docs-to-developer-hub.sh\ to sync markdown documentation and build API references into a developer hub repository, ensuring paths are resolved absolutely before changing directories.
scripts · high confidence
New server examples for exposing workflows as HTTP APIs
Added \examples/server\ with documentation and runnable code demonstrating how to use \WorkflowServer\ to expose workflows as HTTP services. The examples show how to run the server standalone or mount it as a sub-application within an existing FastAPI app, and include notebooks and scripts illustrating event streaming via Server-Sent Events (SSE) for real-time progress updates.
examples/server · high confidence
Repository initialization with LlamaAgents monorepo structure and tooling
The repository has been initialized as a monorepo for the LlamaAgents project, establishing the foundational structure and development tooling. This includes a \uv.lock\ file for Python dependency management across multiple packages (such as \llama-index-workflows\, \llama-agents-server\, and \llamactl\), a \pnpm-workspace.yaml\ for JavaScript/TypeScript tooling, and configuration files for pre-commit hooks (Ruff, basedpyright, ty) and code formatting. The project also introduces new documentation guides (\AGENTS.md\, \CLAUDE.md\) for development workflows and removes legacy build artifacts like \BUILD\ and \\_\init\\_.py\ files that were part of the previous \llama\_index.core.workflow\ structure.
(repo-wide) · high confidence
Server runtime now persists workflow events and manages handler lifecycle
The server runtime now records all workflow events to a configured store, ensuring that run state and history are preserved and queryable. It also introduces idle detection and memory management for workflow handlers, automatically releasing idle handlers from memory after a configurable timeout and reloading them on demand to optimize resource usage.
_packages/llama-agents-server/src/llama\_agents/server/\runtime · high confidence
Behavioural changes
Add executor lease tracking to database schema
The database store for DBOS-backed agents now includes an \executor\_leases\ table in both PostgreSQL and SQLite migration scripts. This addition allows the system to track which executor holds a specific slot and monitor heartbeats, enabling dynamic executor management without requiring pre-defined stable executor IDs.
_packages/llama-agents-dbos/src/llama\_agents/dbos/\store · high confidence
Expose typed workflow introspection responses in the client package
The \llama-agents-client\ package now explicitly exports typed response models for workflow introspection, including \WorkflowGraphResponse\, \WorkflowSchemaResponse\, \WorkflowEventsListResponse\, \HandlersListResponse\, \CancelHandlerResponse\, \SendEventResponse\, and \HandlerData\. This allows users to interact with the \WorkflowClient\ using strongly-typed data structures for querying workflow graphs, schemas, event histories, and handler states, improving type safety and developer experience when building agent workflows.
packages/llama-agents-client/src · high confidence
Introduce llama\_agents core library with backward-compatible llama\_deploy alias
This change establishes the \llama\_agents\ package as the primary implementation for core deployment, backup, and project management capabilities, replacing the previous \llama\_deploy\ namespace. To ensure backward compatibility, a meta-path finder is installed that transparently redirects any \llama\deploy.\\ imports to \llama\agents.\\, allowing existing code to continue functioning without modification. The new core library introduces a comprehensive set of Pydantic schemas for deployments, backups, and projects, along with an async HTTP client (\ControlPlaneClient\, \ProjectClient\) for interacting with the management API, and utility modules for SSL configuration, iterator buffering, and path validation.
packages/llama-agents-core/src · high confidence
Refactored server architecture with durable workflow runtime and improved error handling
The server package has been restructured to separate concerns into a dedicated service layer (\_WorkflowService), a durable runtime (\_DurableWorkflowRuntime), and an API layer (\WorkflowAPI). This change introduces a new KeyedLock utility for per-key mutual exclusion and an LRU cache for efficient data access. The WorkflowServer now supports configurable persistence backoff, SSE heartbeats to prevent idle connection drops, and an optional context API for submitting saved state. Error handling is improved with structured JSON responses for 500 errors and better logging. The package also adds new stores like AgentDataStore and MemoryWorkflowStore, and renames the package from llama-index-workflows-\ to llama-agents-\*.
_packages/llama-agents-server/src/llama\agents/server · high confidence
Reworked workflow package structure and event routing
The \llama-index-workflows\ package has been restructured to support the \llama-agents\ namespace, introducing a meta-path finder that aliases \llama\_agents.workflows\ to the core \workflows\ package. This change centralizes event-type matching logic, enabling both exact and subclass-aware event routing for workflow steps. Additionally, the package now includes a new \workflows.client\ module that re-exports \WorkflowClient\ from the optional \llama-agents-client\ package, providing a deprecation warning for direct imports from the old location.
packages/llama-index-workflows/src · high confidence
SQLite store refactored with schema migrations and WAL mode
The SQLite workflow store now uses a formal migration system (migrate.py and SQL files) to manage schema evolution, including new tables for ticks, events, and workflow state, and extended columns on handlers. It enables WAL journal mode for better concurrent access and adds a single-connection mode (using the unix-none VFS) to avoid locking issues in single-process scenarios.
_packages/llama-agents-server/src/llama\_agents/server/\store/sqlite · high confidence
Update debugger assets to version 0.2.42
The static entry point for the workflow debugger has been updated to load version 0.2.42 of the @llamaindex/workflow-debugger library from the jsDelivr CDN, replacing the previous version references in the HTML file.
_packages/llama-agents-server/src/llama\agents/server/static · high confidence
Workflow visualization and representation enhancements
The workflow utility module now provides improved graph visualization and representation capabilities. It supports rendering nested workflows and includes specific node types for resources and resource configurations in the workflow graph. Visualization outputs (Pyvis and Mermaid) have been updated to distinguish these new node types with specific colors and shapes, and Mermaid execution step IDs are now sanitized to handle slashes correctly. Additionally, workflow names are included in the workflow graph export, and the system reads workflows from globals rather than sys modules to support better runtime plugin architecture.
packages/llama-index-utils-workflow/src · high confidence
llamactl CLI restructured with new command groups and shell completion
The llamactl CLI has been reorganized into a new modular structure with dedicated command groups for agents, deployments, authentication, environments, and development utilities. A new shell completion system has been added, supporting bash, zsh, and fish with auto-installation capabilities. The authentication flow now supports both API key and OIDC browser login with profile management. Deployment management includes YAML-based apply functionality with environment variable resolution and error annotation. The CLI now provides better error handling for OIDC configuration issues and supports non-interactive authentication modes.
packages/llamactl/src · high confidence
Test coverage
2 commits adding/updating tests in packages/llama-agents-appserver/tests/routers; Added DBOS integration test fixtures for workflow execution and server simulation; Added comprehensive test coverage for LlamaIndex Workflows; Added comprehensive test suite for llamactl CLI; Added comprehensive test suite for workflow context state management and serialization; Added comprehensive tests for WorkflowClient functionality; Added integration tests for DBOS workflow execution and resilience; Added runtime test suite for workflow execution and state management; Added test coverage for core client, deployment, and utility modules; Added tests for backup, code repo, deployment, and build subsystems; Added tests for protocol event serialization and deserialization; Added tests for the dev CLI; Added tests for workflow visualization and resource handling; Expanded test coverage for llama-agents-server components; Initial test suite for llama-agents-agentcore; Initial test suite for the Llama Agents App Server; Integration test suite for llama-agents workflows and stores; New integration test infrastructure for llama-agents; Operator controller tests for namespace isolation, pod classification, and rollout lifecycle.
Dependencies
Initialize LlamaAgents monorepo with unified build tooling and dependency manifests
This change introduces the foundational structure for the LlamaAgents monorepo, establishing a unified workspace that coordinates multiple Python and TypeScript packages. It adds \pyproject.toml\ and \package.json\ manifests for core components including \llama-index-workflows\, \llama-agents-server\, \llama-agents-client\, \llama-agents-core\, \llama-agents-appserver\, \llama-agents-control-plane\, \llamactl\, and the Kubernetes operator. The configuration standardizes the build system to \uv\ (using \uv\_build\) for Python packages and \pnpm\ for the workspace, while defining explicit dependency ranges (e.g., \llama-index-workflows\>=2.21.0\ for the server) and dev tooling like \pytest\, \ruff\, and \basedpyright\. It also includes the Go module definition for the operator and Helm chart metadata, effectively setting up the dependency graph and versioning strategy for the entire suite.
(dependencies) · high confidence
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
How this codebase got here
Score
- CAI 54 → 58 (+4.5)
- Rubric changed (rubric-2026.10.5 → rubric-2026.11.2) — scores are not directly comparable.
Lenses
- Code Health 64 → 64 (-0.0)
- Architecture 97 → 97 (+0.2)
- Maturity 46 → 76 (+29.4)
- Readiness 53 → 53 (+0.0)
- Security 73 → 74 (+0.3)
- Accessibility 59 → 53 (-6.3)
- Performance 85 → 85 (+0.0)
Resolved (28)
- Critical CVE: [GHSA redacted] (uv.lock)
- Critical vulnerability: [GHSA redacted] (uv.lock)
- Critical vulnerability: [GHSA redacted] (uv.lock)
- Duplicate intent with different signatures. 'previous_tag' takes a pre-fetched list of tags, while 'find_previous_tag' takes a repo path and prefix to fetch tags internally. This creates two ways to achieve the same goal (finding the previous tag) with different responsibilities (caller vs callee fetching tags).
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (pnpm-lock.yaml)
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (pnpm-lock.yaml)
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (pnpm-lock.yaml)
- Inconsistent naming convention for command execution. 'run_command' implies a generic runner, while 'run_and_capture' is specific to output capture. This suggests a potential missing 'run' method that returns output, or an inconsistent split between void and return-value methods.
- Inconsistent parameter naming and structure for similar 'is_published' checks. 'is_published' takes 'name' and 'version', 'is_docker_image_published' takes 'repository' and 'tag', and 'is_helm_chart_published' takes 'chart_name' and 'version'. The domain concepts (name vs repository vs chart_name) are not abstracted into a common interface or consistent naming.
- Medium CVE: [GHSA redacted] (uv.lock)
- Medium CVE: [GHSA redacted] (uv.lock)
- Medium CVE: [GHSA redacted] (uv.lock)
- Medium CVE: [GHSA redacted] (uv.lock)
- …and 8 more
New (6)
- Documentation: no build, run or usage example (packages/llama-agents-appserver/README.md)
- Documentation: no build, run or usage example (packages/llama-agents-control-plane/README.md)
- Documentation: no build, run or usage example (packages/llama-agents-core/README.md)
- High CVE: [GHSA redacted] (uv.lock)
- High CVE: [GHSA redacted] (uv.lock)
- Off-boarding risk: anonymized user #1
Changes since last survey
- 19 commits — 16 feature/other, 3 fixes
By area
- (root) — 12 commits
- packages/llama-agents-appserver — 3 commits
- operator/go.mod — 2 commits
- .changeset/debian-security-updates-brotli.md — 1 commit
- charts/llama-agents — 1 commit
Notable commits
- fix: Serve pushed deployment UIs from a fixed link in the build artifact (#824)
- fix: fix: repair uv.lock (duplicate pymdown-extensions entry breaks CI on main) (#883)
- fix: npm security fix: overrides + relock for open Dependabot alerts (#887)
- change: Apply Debian security updates in the appserver and control plane images (#846)
- change: Bump the llama-agents chart on any image package release (#832)
- change: Keep UI directory redirects on the public origin (#823)
- change: Python security relock + 3-day uv release-age hold (#885)
- change: Require starlette>=1.0.1 in the appserver and server ([CVE redacted]) (#840)
- change: Update dependency copier to v9.15.2 [SECURITY] (#871)
- change: Update dependency dulwich to v1.2.9 [SECURITY] (#869)
- change: Update dependency gitpython to v3.2.1 [SECURITY] (#872)
- change: Update dependency mkdocs-material to v9.7.7 [SECURITY] (#870)
- change: Update dependency pyjwt to v2.15.0 [SECURITY] (#873)
- change: Update dependency pymdown-extensions to v11 [SECURITY] (#877)
- change: Update module github.com/google/cel-go to v0.30.0 [SECURITY] (#874)
- change: Update module golang.org/x/net to v0.62.0 [SECURITY] (#875)
- change: Update pnpm to v10.34.5 [SECURITY] (#876)
- change: chore: version packages (#826)
- change: chore: version packages (#833)
Architecture
- Unchanged — 0 containers · 1 contexts · 0 edges
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
run-llama/llama-agents was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.
About this page
- The score is its most recent published measurement, taken on 10 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
- Measured at commit 6019e81075ca18f21457813e6437c49c9e57be24 — the exact code this score is about.
- Scored under rubric-2026.11.2 — the same rubric and the same method as every other entry in this index.
- Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.4+preprod-464a0040a931.