⚙️ Ship — 3 items
📦 LiteLLM registry: 20 new models priced — LiteLLM registry adds pricing for 20 Azure AI models — DeepSeek V3.2/V4-Pro and GLM 5/5.1/5.2 among them. Cost tracking for those endpoints now works out of the box.
📦 Qwen3.8 27B live on OpenRouter — Qwen3.8 27B now on OpenRouter — a mid-size Qwen model for cost-sensitive agent deployments. Pricing and provider availability on the model page.
📦 Qwen Code v0.21.13: SWE-bench 500, Terminal-Bench 89 — Qwen Code v0.21.13 validated end-to-end: 500 on SWE-bench Verified, 89 on Terminal-Bench 2.0. The release is pinned to these results — a concrete benchmark point for harness evaluation.
Model availability and benchmark validation day — new Qwen options on OpenRouter and LiteLLM pricing, plus a concrete SWE-bench number for Qwen Code. If you're cost-optimizing or evaluating harnesses, today's data points are worth a look.
📦 LiteLLM registry: 20 new models priced — LiteLLM registry adds pricing for 20 Azure AI models — DeepSeek V3.2/V4-Pro and GLM 5/5.1/5.2 among them. Cost tracking for those endpoints now works out of the box.
📦 Qwen3.8 27B live on OpenRouter — Qwen3.8 27B now on OpenRouter — a mid-size Qwen model for cost-sensitive agent deployments. Pricing and provider availability on the model page.
📦 Qwen Code v0.21.13: SWE-bench 500, Terminal-Bench 89 — Qwen Code v0.21.13 validated end-to-end: 500 on SWE-bench Verified, 89 on Terminal-Bench 2.0. The release is pinned to these results — a concrete benchmark point for harness evaluation.
Model availability and benchmark validation day — new Qwen options on OpenRouter and LiteLLM pricing, plus a concrete SWE-bench number for Qwen Code. If you're cost-optimizing or evaluating harnesses, today's data points are worth a look.
GitHub
litellm/model_prices_and_context_window.json at main · BerriAI/litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr...
💬 Community — 4 items
💬 Second Thought: Reasoning in Parallel as LLM Agents Act and Observe — Training-free framework runs auxiliary reasoning branches in parallel during action-observation waits, turning idle time into test-time compute — drop-in for latency-bound agent loops.
💬 Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development — Systematic eval of long-horizon AI R&D agents finds strong engineering optimization but unstable performance, limited novelty, and variable experience reuse — a reality check for autonomous research bets.
💬 Latent On-Policy Self-Distillation — Learns privileged teaching context end-to-end from experience to provide dense token-level supervision — a training-time trick that could improve agent policy learning without extra labels.
💬 Launch HN: Speko (YC S26) – OpenRouter for Voice AI — Benchmarks speech-to-text, LLM, and TTS combos and picks the optimal stack for your constraints — a routing layer for voice agents. 54 points on HN.
Today's signal is about squeezing more from existing agent loops: parallel reasoning during idle waits, better evaluation of long-horizon agents, and routing layers for voice stacks. The common thread is efficiency without new models.
💬 Second Thought: Reasoning in Parallel as LLM Agents Act and Observe — Training-free framework runs auxiliary reasoning branches in parallel during action-observation waits, turning idle time into test-time compute — drop-in for latency-bound agent loops.
💬 Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development — Systematic eval of long-horizon AI R&D agents finds strong engineering optimization but unstable performance, limited novelty, and variable experience reuse — a reality check for autonomous research bets.
💬 Latent On-Policy Self-Distillation — Learns privileged teaching context end-to-end from experience to provide dense token-level supervision — a training-time trick that could improve agent policy learning without extra labels.
💬 Launch HN: Speko (YC S26) – OpenRouter for Voice AI — Benchmarks speech-to-text, LLM, and TTS combos and picks the optimal stack for your constraints — a routing layer for voice agents. 54 points on HN.
Today's signal is about squeezing more from existing agent loops: parallel reasoning during idle waits, better evaluation of long-horizon agents, and routing layers for voice stacks. The common thread is efficiency without new models.
huggingface.co
Paper page - Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
Join the discussion on this paper page
📚 Read — 5 items
📚 DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation — 524M vision-document retriever distilled from an 8B teacher — small enough to run locally in agent pipelines that index scanned docs, no relevance labels needed.
📚 SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information — Benchmarks mobile-assistant LLMs on scattered personal data — finds major gaps in retrieval and verification, a warning for any agent that touches user context.
📚 CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA — Adversarial multi-agent debate for claim-level verification in cross-modal financial QA — a fact-checking pattern that generalizes beyond finance to any high-stakes agent output.
📚 Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems — Inflation-aware routing treats tokens by value, not volume — a cost-optimization approach for agentic systems that could cut spend without dropping quality.
📚 Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents — Governed local-first runtime for tool-using LLM agents — policy controls over what tools an agent can call, aimed at self-hosted deployments that need auditability.
Today's papers converge on two operator levers: cost (token routing) and control (governed runtimes). Both are solvable with current research — the gap is adoption, not capability.
📚 DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation — 524M vision-document retriever distilled from an 8B teacher — small enough to run locally in agent pipelines that index scanned docs, no relevance labels needed.
📚 SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information — Benchmarks mobile-assistant LLMs on scattered personal data — finds major gaps in retrieval and verification, a warning for any agent that touches user context.
📚 CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA — Adversarial multi-agent debate for claim-level verification in cross-modal financial QA — a fact-checking pattern that generalizes beyond finance to any high-stakes agent output.
📚 Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems — Inflation-aware routing treats tokens by value, not volume — a cost-optimization approach for agentic systems that could cut spend without dropping quality.
📚 Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents — Governed local-first runtime for tool-using LLM agents — policy controls over what tools an agent can call, aimed at self-hosted deployments that need auditability.
Today's papers converge on two operator levers: cost (token routing) and control (governed runtimes). Both are solvable with current research — the gap is adoption, not capability.
huggingface.co
Paper page - DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
Join the discussion on this paper page
⚙️ Ship — 4 items
📦 Hermes Agent 2026.8.16 — Hermes Agent v0.20.3 rolls up ~125 PRs: MCP 2.x SDK migration with stateless protocol support, bundled Bot Mode plugin, and subprocess Python runtime isolation (PYTHONHOME/PYTHONPATH). Operators on MCP should test stateless mode; Python subprocess hardening changes runtime behavior.
📦 OpenHands 1.14.0 — OpenHands 1.14.0 adds LLM pre-flight validation to catch misconfigured profiles before saving, a Git Sync page for automations, and sets Canvas default to Kimi K3 (free). Operators configuring profiles get earlier error feedback.
📦 OpenAI SDK 3.2.0 — OpenAI Python SDK 3.2.0 adds Bedrock Runtime endpoint support and shell call streaming events. Operators bridging OpenAI SDK to Bedrock get a direct path; shell call streaming improves real-time tool output.
📦 PR #124528 Gateway profile evidence — OpenClaw ships gateway profile evidence (PR #124528) — likely new audit/telemetry for gateway profiles; check release notes for what's now logged.
Protocol migrations and pre-flight validation dominate today — test stateless MCP and profile validation before rolling out.
📦 Hermes Agent 2026.8.16 — Hermes Agent v0.20.3 rolls up ~125 PRs: MCP 2.x SDK migration with stateless protocol support, bundled Bot Mode plugin, and subprocess Python runtime isolation (PYTHONHOME/PYTHONPATH). Operators on MCP should test stateless mode; Python subprocess hardening changes runtime behavior.
📦 OpenHands 1.14.0 — OpenHands 1.14.0 adds LLM pre-flight validation to catch misconfigured profiles before saving, a Git Sync page for automations, and sets Canvas default to Kimi K3 (free). Operators configuring profiles get earlier error feedback.
📦 OpenAI SDK 3.2.0 — OpenAI Python SDK 3.2.0 adds Bedrock Runtime endpoint support and shell call streaming events. Operators bridging OpenAI SDK to Bedrock get a direct path; shell call streaming improves real-time tool output.
📦 PR #124528 Gateway profile evidence — OpenClaw ships gateway profile evidence (PR #124528) — likely new audit/telemetry for gateway profiles; check release notes for what's now logged.
Protocol migrations and pre-flight validation dominate today — test stateless MCP and profile validation before rolling out.
GitHub
Release Hermes Agent v0.20.3 (2026.8.16.2) · NousResearch/hermes-agent
Hermes Agent v0.20.3 (v2026.8.16.2)
Release Date: August 16, 2026
Patch release. This tag rolls up the ~125 PRs merged since v0.20.2 into a stable tagged release for downstream consumers (Docker i...
Release Date: August 16, 2026
Patch release. This tag rolls up the ~125 PRs merged since v0.20.2 into a stable tagged release for downstream consumers (Docker i...
📚 Read — 5 items
📚 ClawGym II: Exploring Black-Box RL on Agent Harness — Black-box RL framework for optimizing agents through complex harnesses — stable, scalable optimization without white-box access, aimed at long-horizon task performance.
📚 Agentic Transaction: Towards ACID-Compliant Agent Systems — ACID-style transactions for LLM agents — semantic guarantees for reliable, isolated, durable execution, moving agent workflows toward database-grade consistency.
📚 VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End? — Agentic RL framework for end-to-end 3D world construction — agents infer intent, plan scenes, invoke tools, and reflect on feedback; benchmarks expose where multimodal agents still fail.
📚 Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study — Measurement study on whether language servers reduce token consumption for coding agents — preliminary results for anyone optimizing context budgets.
📚 Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation — Reward-free judging rubrics to reduce over-crediting in agent evaluation — addresses LLM judges inflating scores, a known eval failure mode.
Agent evaluation and reliability are converging: black-box RL for harness tuning, ACID transactions for execution guarantees, and rubrics to stop over-crediting. The tooling is maturing past 'does it work' to 'can we trust it'.
📚 ClawGym II: Exploring Black-Box RL on Agent Harness — Black-box RL framework for optimizing agents through complex harnesses — stable, scalable optimization without white-box access, aimed at long-horizon task performance.
📚 Agentic Transaction: Towards ACID-Compliant Agent Systems — ACID-style transactions for LLM agents — semantic guarantees for reliable, isolated, durable execution, moving agent workflows toward database-grade consistency.
📚 VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End? — Agentic RL framework for end-to-end 3D world construction — agents infer intent, plan scenes, invoke tools, and reflect on feedback; benchmarks expose where multimodal agents still fail.
📚 Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study — Measurement study on whether language servers reduce token consumption for coding agents — preliminary results for anyone optimizing context budgets.
📚 Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation — Reward-free judging rubrics to reduce over-crediting in agent evaluation — addresses LLM judges inflating scores, a known eval failure mode.
Agent evaluation and reliability are converging: black-box RL for harness tuning, ACID transactions for execution guarantees, and rubrics to stop over-crediting. The tooling is maturing past 'does it work' to 'can we trust it'.
huggingface.co
Paper page - ClawGym II: Exploring Black-Box RL on Agent Harness
Join the discussion on this paper page
💬 Community — 1 item
💬 GPT-5.6 Sol Pricing Cut by 50% — OpenRouter cuts GPT-5.6 Sol pricing 50%. 177-point HN thread of operators comparing it to Claude — the throughline: capable model, far fewer thinking tokens. Real cost signal for agent workloads.
The cost floor for agent inference keeps dropping. A 50% cut on a capable, token-efficient model means operators should re-benchmark model choices quarterly, not annually.
💬 GPT-5.6 Sol Pricing Cut by 50% — OpenRouter cuts GPT-5.6 Sol pricing 50%. 177-point HN thread of operators comparing it to Claude — the throughline: capable model, far fewer thinking tokens. Real cost signal for agent workloads.
The cost floor for agent inference keeps dropping. A 50% cut on a capable, token-efficient model means operators should re-benchmark model choices quarterly, not annually.
⚙️ Ship — 2 items
📦 Hermes Agent v2026.8.18 — Hermes Agent v2026.8.18 — stable tag rolling up ~74 PRs: desktop glass/translucency surface, tabbed SESSIONS|BOTS sidebar, Bot Mode group-chat fixes, NVIDIA SkillEvaluator Tier 1 advisory scanning on skill installs, cron media-send hardening.
📦 Qwen3.8-27B-Uncensored-GGUF trending on Hugging Face — Qwen3.8-27B-Uncensored-GGUF is trending on HF — 357k downloads, 307 likes. A 27B uncensored Qwen variant in GGUF; local agent builders are pulling it.
Hermes is consolidating a big merge window into a stable tag; operators on downstream Docker/hosted deployments should pull this before the next feature wave.
📦 Hermes Agent v2026.8.18 — Hermes Agent v2026.8.18 — stable tag rolling up ~74 PRs: desktop glass/translucency surface, tabbed SESSIONS|BOTS sidebar, Bot Mode group-chat fixes, NVIDIA SkillEvaluator Tier 1 advisory scanning on skill installs, cron media-send hardening.
📦 Qwen3.8-27B-Uncensored-GGUF trending on Hugging Face — Qwen3.8-27B-Uncensored-GGUF is trending on HF — 357k downloads, 307 likes. A 27B uncensored Qwen variant in GGUF; local agent builders are pulling it.
Hermes is consolidating a big merge window into a stable tag; operators on downstream Docker/hosted deployments should pull this before the next feature wave.
GitHub
Release Hermes Agent v0.20.4 (2026.8.18) · NousResearch/hermes-agent
Hermes Agent v0.20.4 (v2026.8.18)
Release Date: August 18, 2026
Patch release. This tag rolls up the ~74 PRs merged since v0.20.3 into a stable tagged release for downstream consumers (Docker imag...
Release Date: August 18, 2026
Patch release. This tag rolls up the ~74 PRs merged since v0.20.3 into a stable tagged release for downstream consumers (Docker imag...
💬 Community — 4 items
💬 HarnessEval-W — A paper proposing a pipeline that uses hierarchical sub-agents to verify reasoning chains in visual world evaluations.
💬 R^3-Bench — A benchmark claiming LLMs underperform when managing a shared computation budget across multiple problems.
💬 UI-Mate — An open-weight GUI agent using environment-grounded training and in-context demonstrations to increase reliability.
💬 1667 — A terminal UI for LLM-assisted fiction writing (35 points on HN).
💬 HarnessEval-W — A paper proposing a pipeline that uses hierarchical sub-agents to verify reasoning chains in visual world evaluations.
💬 R^3-Bench — A benchmark claiming LLMs underperform when managing a shared computation budget across multiple problems.
💬 UI-Mate — An open-weight GUI agent using environment-grounded training and in-context demonstrations to increase reliability.
💬 1667 — A terminal UI for LLM-assisted fiction writing (35 points on HN).
huggingface.co
Paper page - HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Join the discussion on this paper page
📚 Read — 5 items
📚 How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks — 100 real-world frontier research tasks; agents fail pervasively on metacognitive self-correction and motivation, not raw capability — the gap to close before trusting autonomous research loops.
📚 Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs — Black-box probes of hosted open-weight APIs measure fidelity drift under repeated and long-sequence use — useful for anyone pinning model behavior in production.
📚 Amp adds realtime voice chat with Puck — Amp adds realtime voice chat with Puck — gpt-realtime-2.1 summarizes agent responses aloud while full text lands in thread. Hands-off supervision without staring at the terminal.
📚 Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents — Taxonomy of how misunderstandings arise, amplify, and get detected in agent interactions — useful framing for debugging multi-turn agent failures.
📚 GitHub Copilot weekly releases — August 10 — Copilot weekly changelog covers VS Code 1.133, JetBrains, CLI — scan for agent-mode changes if you run Copilot in CI.
Research day: the failure modes are metacognitive, not capability. Operators should instrument self-correction, not just benchmark task completion.
📚 How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks — 100 real-world frontier research tasks; agents fail pervasively on metacognitive self-correction and motivation, not raw capability — the gap to close before trusting autonomous research loops.
📚 Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs — Black-box probes of hosted open-weight APIs measure fidelity drift under repeated and long-sequence use — useful for anyone pinning model behavior in production.
📚 Amp adds realtime voice chat with Puck — Amp adds realtime voice chat with Puck — gpt-realtime-2.1 summarizes agent responses aloud while full text lands in thread. Hands-off supervision without staring at the terminal.
📚 Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents — Taxonomy of how misunderstandings arise, amplify, and get detected in agent interactions — useful framing for debugging multi-turn agent failures.
📚 GitHub Copilot weekly releases — August 10 — Copilot weekly changelog covers VS Code 1.133, JetBrains, CLI — scan for agent-mode changes if you run Copilot in CI.
Research day: the failure modes are metacognitive, not capability. Operators should instrument self-correction, not just benchmark task completion.
huggingface.co
Paper page - How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks
Join the discussion on this paper page
⚙️ Ship — 3 items
📦 Codex 0.148.0 — Hooks go async and can call MCP tools; `/export` saves TUI sessions to Markdown, `/status` shows thread cost, and Amazon Bedrock Runtime joins as a built-in provider.
📦 Claude platform release notes — August 18, 2026 — Workbench is now Playground in the Claude Console — supports every Messages API parameter, shows the full SDK request and API response per run, and includes templates for code execution and web search.
📦 OpenAI SDK 3.3.0 — OpenAI Python SDK 3.3.0 adds named data-residency endpoints, letting orgs pin API traffic to specific regions for compliance.
Between Codex's async hooks and OpenAI's data-residency endpoints, operators get more control over how agent traffic runs and where it lands. Worth testing before your next pipeline refactor.
📦 Codex 0.148.0 — Hooks go async and can call MCP tools; `/export` saves TUI sessions to Markdown, `/status` shows thread cost, and Amazon Bedrock Runtime joins as a built-in provider.
📦 Claude platform release notes — August 18, 2026 — Workbench is now Playground in the Claude Console — supports every Messages API parameter, shows the full SDK request and API response per run, and includes templates for code execution and web search.
📦 OpenAI SDK 3.3.0 — OpenAI Python SDK 3.3.0 adds named data-residency endpoints, letting orgs pin API traffic to specific regions for compliance.
Between Codex's async hooks and OpenAI's data-residency endpoints, operators get more control over how agent traffic runs and where it lands. Worth testing before your next pipeline refactor.
GitHub
Release 0.148.0 · openai/codex
New Features
Export complete TUI conversations to Markdown with /export, either to the clipboard or a new file. (#37358)
Fork sessions with codex exec fork, and archive or restore sessions from th...
Export complete TUI conversations to Markdown with /export, either to the clipboard or a new file. (#37358)
Fork sessions with codex exec fork, and archive or restore sessions from th...
📚 Read — 4 items
📚 Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements — Agentic ESOpt fine-tunes long-horizon LLM agents with evolution strategies and trajectory-level rewards — full-parameter tuning without the GPU bill. Worth a look if you're training agents on limited hardware.
📚 From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents — RUPA models agent trajectories as relational graphs to propagate uncertainty across long runs — better failure detection and confidence calibration for multi-step agents.
📚 ASI-Bench: At the Dawn of Artificial Superintelligence — ASI-Bench evaluates agents on scientific exploration and innovation tasks — a benchmark for measuring how far current agents are from autonomous research.
📚 AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search — AutoMem uses text-gradient recursive self-improvement to automatically search memory architectures for agents — memory design as an optimization problem rather than hand-tuning.
Today's Read lane is about making agents more reliable and cheaper to train: uncertainty propagation, automated memory search, and low-GPU fine-tuning all point the same direction.
📚 Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements — Agentic ESOpt fine-tunes long-horizon LLM agents with evolution strategies and trajectory-level rewards — full-parameter tuning without the GPU bill. Worth a look if you're training agents on limited hardware.
📚 From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents — RUPA models agent trajectories as relational graphs to propagate uncertainty across long runs — better failure detection and confidence calibration for multi-step agents.
📚 ASI-Bench: At the Dawn of Artificial Superintelligence — ASI-Bench evaluates agents on scientific exploration and innovation tasks — a benchmark for measuring how far current agents are from autonomous research.
📚 AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search — AutoMem uses text-gradient recursive self-improvement to automatically search memory architectures for agents — memory design as an optimization problem rather than hand-tuning.
Today's Read lane is about making agents more reliable and cheaper to train: uncertainty propagation, automated memory search, and low-GPU fine-tuning all point the same direction.
huggingface.co
Paper page - Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
Join the discussion on this paper page
💬 Community — 1 item
💬 Devin cuts GPT-5.6 Sol pricing 70% — Devin drops GPT-5.6 Sol pricing 70% — worth checking if your Devin workloads are on that model; HN thread is light on comments so far.
Pricing pressure on coding agents is real; when a major harness cuts a model's cost 70%, it's worth re-evaluating your own per-task economics.
💬 Devin cuts GPT-5.6 Sol pricing 70% — Devin drops GPT-5.6 Sol pricing 70% — worth checking if your Devin workloads are on that model; HN thread is light on comments so far.
Pricing pressure on coding agents is real; when a major harness cuts a model's cost 70%, it's worth re-evaluating your own per-task economics.
⚙️ Ship — 2 items
📦 OpenAI Agents SDK 0.22.0 — OpenAI Agents SDK 0.22.0 — guardrail-rejected tool output is now redacted from replay/persisted state, and non-streaming Responses with terminal `failed`/`incomplete` raise `ModelBehaviorError`. Breaking: if you pass an explicit `openai_client` with `organization`/`project`, move those to the `AsyncOpenAI` client.
📦 Anthropic SDK 0.118.0 — Anthropic SDK 0.118.0 — adds files/memory store API surface and workspace-ID helpers; session-runner retries tool-result sends for the lease TTL, and docs now warn that blocking tool bodies stall the worker heartbeat.
Runtime-hardening day: both SDKs tighten state handling and provider contracts — worth a quick migration check if you pass explicit clients or rely on replayable traces.
📦 OpenAI Agents SDK 0.22.0 — OpenAI Agents SDK 0.22.0 — guardrail-rejected tool output is now redacted from replay/persisted state, and non-streaming Responses with terminal `failed`/`incomplete` raise `ModelBehaviorError`. Breaking: if you pass an explicit `openai_client` with `organization`/`project`, move those to the `AsyncOpenAI` client.
📦 Anthropic SDK 0.118.0 — Anthropic SDK 0.118.0 — adds files/memory store API surface and workspace-ID helpers; session-runner retries tool-result sends for the lease TTL, and docs now warn that blocking tool bodies stall the worker heartbeat.
Runtime-hardening day: both SDKs tighten state handling and provider contracts — worth a quick migration check if you pass explicit clients or rely on replayable traces.
GitHub
Release v0.22.0 · openai/openai-agents-python
Key Changes
Version 0.22.0 is a minor release because it adds substantial runtime hardening and tightens an existing provider configuration contract. Applications that combine an explicit openai_cl...
Version 0.22.0 is a minor release because it adds substantial runtime hardening and tightens an existing provider configuration contract. Applications that combine an explicit openai_cl...
💬 Community — 3 items
💬 LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents — Open-source framework for harness-native RL on coding agents — in-process LLM proxying and sandbox orchestration let you policy-gradient-train the agent inside its actual harness, not a stripped-down eval loop.
💬 Agent Lightning v1.0: Towards Harnessed Agentic RL — Reproducible RL for arbitrary agent harnesses — trains the full agent stack (harness + LLM) and reports substantial coding-agent gains. Worth a look if you've been RL-tuning models in isolation.
💬 StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows — Benchmarks general-purpose agents on market-validated startup workflows end-to-end; even top models finish only ~30% of tasks. A reality check on how far agents are from replacing a junior operator.
The RL-for-agents field is converging on harness-native training. If you're building coding agents, the question is no longer whether to RL-tune, but which harness integration you'll adopt.
💬 LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents — Open-source framework for harness-native RL on coding agents — in-process LLM proxying and sandbox orchestration let you policy-gradient-train the agent inside its actual harness, not a stripped-down eval loop.
💬 Agent Lightning v1.0: Towards Harnessed Agentic RL — Reproducible RL for arbitrary agent harnesses — trains the full agent stack (harness + LLM) and reports substantial coding-agent gains. Worth a look if you've been RL-tuning models in isolation.
💬 StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows — Benchmarks general-purpose agents on market-validated startup workflows end-to-end; even top models finish only ~30% of tasks. A reality check on how far agents are from replacing a junior operator.
The RL-for-agents field is converging on harness-native training. If you're building coding agents, the question is no longer whether to RL-tune, but which harness integration you'll adopt.
huggingface.co
Paper page - LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents
Join the discussion on this paper page
📚 Read — 4 items
📚 HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety — Benchmarks agent harness safety across six operational phases — configuration vulnerabilities and detection gaps are the weak points, not model behavior.
📚 MCP in Orbs — Amp adds remote MCP server support across orbs, the TUI, and Puck — Streamable HTTP with OAuth. Connect hosted servers from ampcode.com/settings/mcp-servers.
📚 Replit expands access to software creation with GPT-5.6 Luna — Replit adds GPT-5.6 Luna as a model option for software creation — a new capability for Replit Agent users.
📚 Cross-Model Memory Transfer via Target-Side Reader Adaptation — Cross-model memory transfer via target-side reader adaptation — lets a model inherit memory from another without retraining, relevant for agent memory portability.
Harness safety and MCP plumbing are the day's themes — operators should audit config surfaces and expect MCP support as default.
📚 HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety — Benchmarks agent harness safety across six operational phases — configuration vulnerabilities and detection gaps are the weak points, not model behavior.
📚 MCP in Orbs — Amp adds remote MCP server support across orbs, the TUI, and Puck — Streamable HTTP with OAuth. Connect hosted servers from ampcode.com/settings/mcp-servers.
📚 Replit expands access to software creation with GPT-5.6 Luna — Replit adds GPT-5.6 Luna as a model option for software creation — a new capability for Replit Agent users.
📚 Cross-Model Memory Transfer via Target-Side Reader Adaptation — Cross-model memory transfer via target-side reader adaptation — lets a model inherit memory from another without retraining, relevant for agent memory portability.
Harness safety and MCP plumbing are the day's themes — operators should audit config surfaces and expect MCP support as default.
huggingface.co
Paper page - HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
Join the discussion on this paper page
⚙️ Ship — 4 items
📦 openclaw release-publish/abd63c06c2f5-1786646045 — New release.
📦 Codex 0.147.0 — New Codex release.
📦 Gemini CLI 0.56.0 — New Gemini release.
📦 Claude Platform — Files API and Enterprise Admin API endpoints are now generally available.
📦 openclaw release-publish/abd63c06c2f5-1786646045 — New release.
📦 Codex 0.147.0 — New Codex release.
📦 Gemini CLI 0.56.0 — New Gemini release.
📦 Claude Platform — Files API and Enterprise Admin API endpoints are now generally available.
GitHub
Release release-publish/abd63c06c2f5-1786646045 · openclaw/openclaw
OpenClaw GitHub-hosted npm preflight tooling for 2026.8.1-beta.2
💬 Community — 3 items
💬 SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution — SkillForge lets agents self-distill repo-specific skills by synthesizing issues, then reusing them to resolve real ones — a step toward agents that onboard themselves to a codebase.
💬 Demystifying Agent Skills: Why They Work-Until They Don't — Skills work by anchoring execution procedurally, not by adding knowledge — and they break when the procedure doesn't match the task. Useful for deciding when to encode a skill vs. rely on the model.
💬 Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents — Controlled eval of memory substrates for long-horizon agents shows no single substrate wins — trade-offs depend on task regime, pushing toward adaptive substrate selection.
Today's papers converge on a theme: agents get better by learning their environment (repo skills, memory substrates), but the gains are regime-dependent — test before you standardize.
💬 SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution — SkillForge lets agents self-distill repo-specific skills by synthesizing issues, then reusing them to resolve real ones — a step toward agents that onboard themselves to a codebase.
💬 Demystifying Agent Skills: Why They Work-Until They Don't — Skills work by anchoring execution procedurally, not by adding knowledge — and they break when the procedure doesn't match the task. Useful for deciding when to encode a skill vs. rely on the model.
💬 Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents — Controlled eval of memory substrates for long-horizon agents shows no single substrate wins — trade-offs depend on task regime, pushing toward adaptive substrate selection.
Today's papers converge on a theme: agents get better by learning their environment (repo skills, memory substrates), but the gains are regime-dependent — test before you standardize.
huggingface.co
Paper page - SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Join the discussion on this paper page
📚 Read — 5 items
📚 Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents — Proposes gating untrusted document access to agents capable of System 2 reasoning, arguing fast pattern-matching agents are vulnerable to prompt injection in RAG pipelines.
📚 KernelArc: A Multi-Agent Framework for GPU Kernel Optimization — Multi-agent framework where specialized agents collaborate on GPU kernel optimization; reports speedups over single-agent baselines and existing autotuners.
📚 SkillEffect: Checked Lowering for Memory-Bounded Agent Tools — Introduces checked lowering for agent tools, enforcing memory bounds at compile time to prevent unbounded memory growth in long-running agents.
📚 GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agents — Structures LLM agents with process-DAG topology for clinical trial programming, targeting reliability in regulated GxP workflows.
📚 aDSL: Agentic 3D Creation via Joint Agent-Program Design — Co-designs a DSL with a multi-agent system for 3D program synthesis; relational operators let agents compose geometry instead of emitting raw code.
Research is converging on guardrails for agent tool use: memory bounds, reasoning gates, and structured topologies are the new reliability primitives.
📚 Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents — Proposes gating untrusted document access to agents capable of System 2 reasoning, arguing fast pattern-matching agents are vulnerable to prompt injection in RAG pipelines.
📚 KernelArc: A Multi-Agent Framework for GPU Kernel Optimization — Multi-agent framework where specialized agents collaborate on GPU kernel optimization; reports speedups over single-agent baselines and existing autotuners.
📚 SkillEffect: Checked Lowering for Memory-Bounded Agent Tools — Introduces checked lowering for agent tools, enforcing memory bounds at compile time to prevent unbounded memory growth in long-running agents.
📚 GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agents — Structures LLM agents with process-DAG topology for clinical trial programming, targeting reliability in regulated GxP workflows.
📚 aDSL: Agentic 3D Creation via Joint Agent-Program Design — Co-designs a DSL with a multi-agent system for 3D program synthesis; relational operators let agents compose geometry instead of emitting raw code.
Research is converging on guardrails for agent tool use: memory bounds, reasoning gates, and structured topologies are the new reliability primitives.
arXiv.org
When Detection Does Not Guarantee Resistance: Reasoning and...
Retrieval-Augmented Generation (RAG) exposes large language models to knowledge-poisoning attacks, where misinformation injected into retrieved documents can influence model outputs. Prior work...
⚙️ Ship — 2 items
📦 Claude Files API and Admin API user management GA — Claude Files API and Enterprise Admin user-management endpoints go GA — beta headers no longer required; file expiration and pagination are now standard.
📦 Anthropic SDK 0.120.0 — Adds managed agents web search config and self-hosted sandbox memory — new knobs for agent search and sandbox persistence.
Platform maturity day: Claude's Files and Admin APIs drop beta headers while the SDK adds managed-agent search and sandbox memory. Operators can start removing beta flags.
📦 Claude Files API and Admin API user management GA — Claude Files API and Enterprise Admin user-management endpoints go GA — beta headers no longer required; file expiration and pagination are now standard.
📦 Anthropic SDK 0.120.0 — Adds managed agents web search config and self-hosted sandbox memory — new knobs for agent search and sandbox persistence.
Platform maturity day: Claude's Files and Admin APIs drop beta headers while the SDK adds managed-agent search and sandbox memory. Operators can start removing beta flags.
Claude Platform Docs
Claude Platform release notes
Updates to the Claude Platform, including the Claude API, client SDKs, and the Claude Console.
💬 Community — 2 items
💬 Claude Code automates neuroscientific data analysis — Eli Sennesh: Claude Code automates most of his one-time job as a neuroscientific data analyst — "which is good, because I super hated that this was an entire job." 61 likes.
💬 Show HN: HarnessRouter: Unified interface for agent harnesses — Canonical API for running Codex, Claude Code, Hermes, and other managed agent harnesses as your product backend. 10 points, 14 comments.
Harness abstraction is the theme: a unified API across Codex/Claude Code/Hermes, and Claude Code already replacing a whole analyst job.
💬 Claude Code automates neuroscientific data analysis — Eli Sennesh: Claude Code automates most of his one-time job as a neuroscientific data analyst — "which is good, because I super hated that this was an entire job." 61 likes.
💬 Show HN: HarnessRouter: Unified interface for agent harnesses — Canonical API for running Codex, Claude Code, Hermes, and other managed agent harnesses as your product backend. 10 points, 14 comments.
Harness abstraction is the theme: a unified API across Codex/Claude Code/Hermes, and Claude Code already replacing a whole analyst job.
Bluesky Social
Eli Sennesh (@elisennesh.bsky.social)
Claude Code basically automates most of my one-time job as a neuroscientific data analyst, which is good, because I super hated that this was an entire job.
[contains quote post or other embedded content]
[contains quote post or other embedded content]