Skip to content

LLM Tooling

Frameworks, runtimes, and infrastructure for building with large language models.

Subscribe
All Breaking Security Features
Important Recent
← Releases
semantic-kernel python-1.43.0 Breaking risk
Breaking changes
  • Update OpenAPI document parsing options (breaking change)
No immediate action
Glq v0.5.1 Breaking risk

Default inline-dequant E8 KV

Open
No immediate action
deepagents deepagents==0.6.8 Breaking risk

Dropped subagent exports

Open
No immediate action
Semble v0.3.2 Breaking risk

Install command + cache override

Open
Review required
Transformers v5.10.1 Breaking risk
Breaking upgrade

Gemma4 Unified Sapiens2 OCR-2 Mellum fixes

Open
No immediate action
docker-agent v1.73.0 Breaking risk

MCP catalog, AI streams, file‑search memory guard

Open
Review required
haystack v2.30.0 Breaking risk
Breaking upgrade

PythonCodeSplitter + string ChatGenerators + async retrievers

Open
No immediate action
Forge v0.7.4 Breaking risk

Tool-error correction + max‑errors flag

Open
Review required
fastmcp v3.4.0 Breaking risk
Auth Breaking upgrade

fastmcp-remote + proxy failure handling + auth token lifespan

Open
Config change
LightRAG v1.5.0 Breaking risk
Breaking upgrade

Multimodal support + native DOCX parsing

Open
Config change
graphify v0.8.29 Breaking risk
Auth

providers.json opt‑in

Open
No immediate action
Aura v1.4.4 Breaking risk

Persisted Worker logs + UI cleanup

Open
Config change
coder v2.34.0 Breaking risk
Breaking upgrade Auth

AI Gateway change + Agents UX + Dashboard

Open
Config change
phoenix arize-phoenix-v17.0.0 Breaking risk
Breaking upgrade

Assistant enablement + trace policy

Open
deepagents deepagents-cli==0.2.0 Breaking risk
Breaking changes
  • `deepagents deploy` now targets the Managed Deep Agents API; `deepagents dev`, `deepagents.toml`, and the `--config`/`--dry-run` flags are removed. Run `deepagents init` to re-scaffold (`agent.json` + `tools.json`).
Notable features
  • Migrate `deepagents deploy` to use Managed Deep Agents API
Review required
hindsight v0.7.2 Breaking risk
Auth Breaking upgrade

api control-plane retain consolidation integrations docs CI perf

Open
No immediate action
Nexa-gauge v0.1.18 Breaking risk

refalign node + refmatch rename

Open
No immediate action
agno v2.6.10 Breaking risk

Model providers, YouTools, DOCX, streaming, run changes

Open
No immediate action
open-webui v0.9.6 Breaking risk

Routine maintenance and dependency updates.

Open
No immediate action
novu v3.17.0 Breaking risk

Breaking changes — review before upgrading.

Open
Ktx v0.8.0 Breaking risk
⚠ Upgrade required
  • Update CI configurations to handle normalized trailing newline in `star-history.svg` and refresh the chart twice daily via RELEASE_PAT on protected main branch.
Breaking changes
  • Removed `fast` mode from `ktx ingest`; ingestion always builds enriched context (KLO-721).
Notable features
  • Added shell completion for commands, flags, and entity names.
  • Enabled PostHog GeoIP enrichment in telemetry.
No immediate action
opik 2.0.54 Breaking risk

Dominant project prompt assignment

Open
No immediate action
docker-agent v1.70.2 Breaking risk

Inline skills + env var handling

Open
LLMKube v0.8.1 Breaking risk
⚠ Upgrade required
  • After upgrading to v0.8.1, re‑apply all Agent CRs so existing Agents pick up explicit values for the new requestTimeoutSeconds and requestTurnTimeoutSeconds fields.
Breaking changes
  • Agent.spec.requestTimeoutSeconds now represents a loop-wide wall-clock budget (default 3600) instead of per-request HTTP timeout; the former behavior is moved to Agent.spec.requestTurnTimeoutSeconds (default 120). Re‑apply Agent CRs after upgrade.
Notable features
  • **inferenceservice:** adds typed spec.ropeScaling for RoPE/YaRN context extension

Beta — feedback welcome: [email protected]