Observed Signal · Apr 10, 2026 · Technical Release · Source: DEV Community · Impact: 2/5 · Sentiment: Positive
asqav SDK v0.2.9 Adds Verification, Attestations, Preflight, Budgets
asqav v0.2.9 was released on PyPI, introducing four developer-facing features for LLM agent workflows: output verification (binding and later verifying hashes of inputs and outputs), portable attestations (self-contained signed documents for external auditors), a consolidated preflight check (single call for status, policy and certificate checks), and client-side budget tracking (BudgetTracker enforces spend limits and signs spend records). The release focuses on tamper-evidence, external verifiability, preventing wasted LLM calls by checking agent readiness, and enforcing API spend ceilings. Documentation and source code are referenced on GitHub and at asqav.com/docs.
A developer SDK release that improves agent security, verifiability, and cost controls—useful for teams building LLM agents but not a major industry-shifting announcement.
Track OpenAI Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- asqav SDK v0.2.9 released on PyPI.
- Output verification: sign_output binds a hash of result to a hash of input; verify_output checks signature validity and output match later.
- Portable attestations: generate_attestation produces a self-contained document with agent public key, session summary, and signatures; verify_attestation validates it without needing the author's keys.
- Preflight: agent.preflight(action) consolidates status, policy_allowed, agent_active and returns reasons when not cleared.
- BudgetTracker enforces client-side spend limits, signs every spend record, rejects negative/NaN/infinite costs, and supports replay against a verification endpoint.
Connected Companies & Entities
1 Entity mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Asqav Ships TypeScript SDK on npm
Asqav published a TypeScript SDK (@asqav/sdk) on npm that mirrors its existing Python SDK and brings agent governance and tamper-evident signing to TypeScript-based AI agents. The npm package is a thin client calling api.asqav.com, exposes the same REST API and behaviour as the Python SDK, and produces ML-DSA-65 (FIPS 204) signatures anchored to Bitcoin via OpenTimestamps for auditability. The SDK is intended to integrate with TypeScript agent frameworks such as Vercel AI SDK, LangChain.js and Mastra to sign tool calls, enabling an audit trail and policy enforcement. The SDK source is available in a GitHub monorepo (MIT license) and the TypeScript and Python SDKs are version-locked at the API level while releases remain independent.
Signed, Reusable Attestations for AI Agent Verification
A developer published a technical post describing a pattern to avoid redundant verification by AI agents: treat verification results as signed, portable, reusable attestations instead of repeated checks. The author describes an implementation (Erabi) that probes paid agent services periodically, publishes JSON attestations signed with Ed25519 over an RFC 8785-canonicalized payload, and exposes endpoints for agents to fetch and verify attestations. The index currently covers 16 pay-per-call services and is open-source (Apache-2.0) on GitHub. The approach aims to reduce wasted calls, latency, and cost by letting agents verify a single signature rather than re-deriving trust each time.
akm 0.7.0 Released with Proposal Queue and Bench
akm 0.7.0 is a technical release that introduces a durable proposal queue for agent-generated changes, three new non-mutating CLI commands (reflect, propose, distill), a first-class "lesson" asset type for synthesized knowledge, opt-in LLM feature gates, and a paired-run benchmarking tool (akm-bench v1). The proposal queue stores drafts outside the asset tree until explicitly accepted, and proposed assets are excluded from default search unless included. Seven bounded in-tree LLM call sites are gated behind llm.features.* flags (all false by default) with a tryLlmFeature() wrapper providing fallbacks and timeouts. The release also includes multiple security, UX, and hygiene hardenings and is opt-in for users upgrading from 0.6.x.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.