| commit |
1.00 |
runner: fix swallowed error in allocModel graph reservation |
|
Commit message contains explicit AI assi |
2026-03-14 |
| commit |
1.00 |
update mlx-c bindings to 0.5.0 (#14380) |
|
Commit message contains explicit AI assi |
2026-02-24 |
| pr |
1.00 |
Add Trepan as a new VS Code extension |
|
PR body explicitly mentions AI collabora |
2026-03-18 |
| commit |
0.00 |
mlxrunner: share KV cache across conversations with common p |
|
— |
2026-03-05 |
| commit |
0.00 |
mlxrunner: fix Slice(0, 0) returning full dimension instead |
|
— |
2026-03-18 |
| commit |
0.00 |
cmd/launch: skip redundant config writes when model unchange |
|
— |
2026-03-18 |
| commit |
0.00 |
docs: update claude code and openclaw for web search (#14922 |
|
— |
2026-03-18 |
| commit |
0.00 |
launch: fix openclaw not picking up newly selected model (#1 |
|
— |
2026-03-18 |
| commit |
0.00 |
docs: update minimax-m2.5 references to m2.7 (#14942) |
|
— |
2026-03-18 |
| commit |
0.00 |
tui: fix signin on headless Linux systems (#14627) |
|
— |
2026-03-18 |
| commit |
0.00 |
launch: disable claude attribution header to preserve KV cac |
|
— |
2026-03-17 |
| commit |
0.00 |
cmd/launch: check for both npm and git before installing Ope |
|
— |
2026-03-18 |
| commit |
0.00 |
launch: register websearch for openclaw (#14914) |
|
— |
2026-03-17 |
| commit |
0.00 |
cloud_proxy: for the web_search legacy path, flush on newlin |
|
— |
2026-03-17 |
| commit |
0.00 |
mlx: quantized embeddings, fast SwiGLU, and runtime fixes (# |
|
— |
2026-03-17 |
| commit |
0.00 |
mlx: add prequantized tensor packing + changes for qwen35 (# |
|
— |
2026-03-17 |
| commit |
0.00 |
sched: Model eviction for MLX |
|
— |
2026-03-02 |
| commit |
0.00 |
launch: fix web search, add web fetch, and enable both for l |
|
— |
2026-03-16 |
| commit |
0.00 |
cmd/launch: skip --install-daemon when systemd is unavailabl |
|
— |
2026-03-16 |
| commit |
0.00 |
bench: improve benchmarking tool (#14240) |
|
— |
2026-03-15 |
| commit |
0.00 |
cmd/launch: add guards for headless mode (#14837) |
|
— |
2026-03-14 |
| commit |
0.00 |
config: use native OpenClaw Ollama onboarding (#14829) |
|
— |
2026-03-13 |
| commit |
0.00 |
rocm: doc driver constraints (#14833) |
|
— |
2026-03-13 |
| commit |
0.00 |
server: decompress zstd request bodies in cloud passthrough |
|
— |
2026-03-13 |
| commit |
0.00 |
launch: remove warning for default policy (#14830) |
|
— |
2026-03-13 |
| commit |
0.00 |
middleware: handle non-JSON error responses gracefully (#148 |
|
— |
2026-03-13 |
| commit |
0.00 |
anthropic: close thinking block before tool_use when no text |
|
— |
2026-03-13 |
| commit |
0.00 |
cmd: still populate `ollama ls` when using `ollama run |
|
— |
2026-03-13 |
| commit |
0.00 |
launch: add compact window for claude code (#14823) |
|
— |
2026-03-13 |
| commit |
0.00 |
api/create: always propagate `:cloud` source for cloud model |
|
— |
2026-03-13 |
| commit |
0.00 |
launch: fix headless --yes integration flow and policy scopi |
|
— |
2026-03-13 |
| commit |
0.00 |
docs: document reasoning_effort support in OpenAI-compatible |
|
— |
2026-03-13 |
| commit |
0.00 |
cmd: TUI model ordering (#14814) |
|
— |
2026-03-13 |
| commit |
0.00 |
server: remove experimental aliases support (#14810) |
|
— |
2026-03-13 |
| commit |
0.00 |
cmd: refactor tui and launch (#14609) |
|
— |
2026-03-13 |
| commit |
0.00 |
ci: fix missing windows zip file (#14807) |
|
— |
2026-03-12 |
| commit |
0.00 |
mlx: perf improvements (#14768) |
|
— |
2026-03-12 |
| commit |
0.00 |
middleware: enable local tool model for web search (#14787) |
|
— |
2026-03-11 |
| commit |
0.00 |
openai: split mixed thinking stream chunks via ToChunks (#14 |
|
— |
2026-03-11 |
| commit |
0.00 |
mlx: only log load errors when MLX is needed (#14764) |
|
— |
2026-03-11 |
| commit |
0.00 |
MLX: harden for init failures (#14777) |
|
— |
2026-03-11 |
| commit |
0.00 |
Revert "runner: add token history sampling parameters to oll |
|
— |
2026-03-11 |
| commit |
0.00 |
config: qwen3.5 recommendations (#14758) |
|
— |
2026-03-11 |
| commit |
0.00 |
cloud_proxy: send ollama client version (#14769) |
|
— |
2026-03-10 |
| commit |
0.00 |
docs: update claude code docs (#14770) |
|
— |
2026-03-10 |
| commit |
0.00 |
server: add experimental web search and web fetch routes (#1 |
|
— |
2026-03-10 |
| commit |
0.00 |
ci: Fix windows build (#14754) |
|
— |
2026-03-10 |
| commit |
0.00 |
MLX: add header vendoring and remove go build tag (#14642) |
|
— |
2026-03-10 |
| commit |
0.00 |
mlx: get parameters from modelfile during model creation (#1 |
|
— |
2026-03-09 |
| commit |
0.00 |
app: auto update should be enabled when reset to defaults (# |
|
— |
2026-03-09 |
| commit |
0.00 |
rocm: update linux to v7.2 (#14391) |
|
— |
2026-03-09 |
| commit |
0.00 |
x/mlxrunner: replace sampler interface chain with single sta |
|
— |
2026-03-08 |
| commit |
0.00 |
cloud_proxy: handle stream disconnects gracefully (#14685) |
|
— |
2026-03-07 |
| commit |
0.00 |
mlx: int4 groupsize 64 (#14682) |
|
— |
2026-03-07 |
| commit |
0.00 |
build: smarter docker parallelism (#14653) |
|
— |
2026-03-07 |
| commit |
0.00 |
create: fix localhost handling (#14681) |
|
— |
2026-03-07 |
| commit |
0.00 |
docs: format compat docs (#14678) |
|
— |
2026-03-06 |
| commit |
0.00 |
Reapply "don't require pulling stubs for cloud models" again |
|
— |
2026-03-06 |
| commit |
0.00 |
parsers: repair unclosed arg_value tags in GLM tool calls (# |
|
— |
2026-03-06 |
| commit |
0.00 |
cmd: override stale entries for context window pi (#14655) |
|
— |
2026-03-06 |
| commit |
0.00 |
mlx: prevent remote creation mismatch (#14651) |
|
— |
2026-03-05 |
| commit |
0.00 |
cmd/config: fix cloud model limit lookups in integrations (# |
|
— |
2026-03-05 |
| commit |
0.00 |
cmd: use native Ollama API endpoint for OpenClaw (#14649) |
|
— |
2026-03-05 |
| commit |
0.00 |
cmd: add qwen3.5 context length for launch (#14626) |
|
— |
2026-03-04 |
| commit |
0.00 |
server: loosen thinking level constraint (#14625) |
|
— |
2026-03-04 |
| commit |
0.00 |
model: fix renderer and parser for qwen3.5 (#14605) |
|
— |
2026-03-04 |
| commit |
0.00 |
Revert "Reapply "don't require pulling stubs for cloud model |
|
— |
2026-03-04 |
| commit |
0.00 |
Add qwen3.5-next-moe support to MLX runner and models (#1441 |
|
— |
2026-03-04 |
| commit |
0.00 |
chore: remove old imagegen LLMs models (#14597) |
|
— |
2026-03-03 |
| commit |
0.00 |
Reapply "don't require pulling stubs for cloud models" |
|
— |
2026-03-03 |
| commit |
0.00 |
model/renderers: fix glm-ocr image tags in renderer prompts |
|
— |
2026-03-03 |
| commit |
0.00 |
Revert "don't require pulling stubs for cloud models (#14574 |
|
— |
2026-03-03 |
| commit |
0.00 |
don't require pulling stubs for cloud models (#14574) |
|
— |
2026-03-03 |
| commit |
0.00 |
mlx: Remove peak memory from the API |
|
— |
2026-03-02 |
| commit |
0.00 |
mlxrunner: Refcount pinned tensors |
|
— |
2026-03-02 |
| commit |
0.00 |
cmd/opencode: rename provider from "Ollama (local)" to "Olla |
|
— |
2026-03-02 |
| commit |
0.00 |
server: verify digest is not empty on create (#14555) |
|
— |
2026-03-02 |
| commit |
0.00 |
runner: add token history sampling parameters to ollama runn |
|
— |
2026-03-02 |
| commit |
0.00 |
model/qwen3next: avoid crash in in DeltaNet when offloading |
|
— |
2026-03-02 |
| commit |
0.00 |
qwen3next: add compatibility with imported GGUF models (#145 |
|
— |
2026-02-28 |
| commit |
0.00 |
mlxrunner: Fix prompt eval timing and count metrics |
|
— |
2026-02-26 |
| commit |
0.00 |
mlxrunner: Enforce model context limit |
|
— |
2026-02-25 |
| commit |
0.00 |
mlxrunner: Propagate pipeline errors to client via api.Statu |
|
— |
2026-02-26 |
| commit |
0.00 |
mlxrunner: Report actual memory usage from runner |
|
— |
2026-02-25 |
| commit |
0.00 |
mlxrunner: Fix panic on full KV cache hit |
|
— |
2026-02-26 |
| commit |
0.00 |
show peak memory usage (#14485) |
|
— |
2026-02-27 |
| commit |
0.00 |
model/parsers: add stable tool call indexing for glm47 and q |
|
— |
2026-02-27 |
| commit |
0.00 |
model: fix qwen3 tool calling in thinking (#14477) |
|
— |
2026-02-27 |
| commit |
0.00 |
fix: window app crash on startup when update is pending (#14 |
|
— |
2026-02-26 |
| commit |
0.00 |
app: fix first update check delayed by 1 hour (#14427) |
|
— |
2026-02-25 |
| commit |
0.00 |
mlxrunner: Cancel in-flight requests when the client disconn |
|
— |
2026-02-24 |
| commit |
0.00 |
mlxrunner: Simplify pipeline memory and cache management |
|
— |
2026-02-24 |
| commit |
0.00 |
model: add support for qwen3.5-27b model (#14415) |
|
— |
2026-02-25 |
| commit |
0.00 |
model: support for qwen3.5 architecture (#14378) |
|
— |
2026-02-25 |
| commit |
0.00 |
ggml: ensure tensor size is valid (#14406) |
|
— |
2026-02-25 |
| commit |
0.00 |
app: add upgrade configuration to settings page (#13512) |
|
— |
2026-02-23 |
| commit |
0.00 |
mlx: don't default to affine quantization for unquantized mo |
|
— |
2026-02-18 |
| commit |
0.00 |
model: improvements to LFM architectures (#14368) |
|
— |
2026-02-23 |
| commit |
0.00 |
mlxrunner: Fix duplicate log prefixes and reduce log noise |
|
— |
2026-02-23 |
| commit |
0.00 |
ui: use capability-based detection for web search (#14336) |
|
— |
2026-02-23 |
| commit |
0.00 |
mlxrunner: Simplify KV cache to single-entry prefix matching |
|
— |
2026-02-20 |
| pr |
0.00 |
Added : OpenAPI spec: ChatStreamEvent missing usage fields i |
|
— |
2026-03-08 |
| pr |
0.00 |
server: prevent system sleep during active inference on Wind |
|
— |
2026-03-19 |
| pr |
0.00 |
use default nvidia-smi as fallback when on WSL2 |
|
— |
2026-01-02 |
| pr |
0.00 |
add uninstall.sh |
|
— |
2026-01-02 |
| pr |
0.00 |
api: check error from json.Unmarshal in checkError |
|
— |
2026-03-19 |
| pr |
0.00 |
model/parsers: fix GLM-4.6 parser returning 500 on truncated |
|
— |
2026-03-18 |
| pr |
0.00 |
iGPU: reduce memory overhead, RAM pressure guard, cap concur |
|
— |
2026-03-19 |
| pr |
0.00 |
docs(openapi): add missing usage fields to ChatStreamEvent |
|
— |
2026-03-16 |
| pr |
0.00 |
app: fix desktop app stuck loading when OLLAMA_HOST is an un |
|
— |
2026-03-16 |
| pr |
0.00 |
server: return 404 when model not found in ChatHandler |
|
— |
2026-03-19 |
| pr |
0.00 |
Fix mlxrunner subprocess deadlocks |
|
— |
2026-03-18 |
| pr |
0.00 |
integration: improve ability to test individual models |
|
— |
2026-03-18 |
| pr |
0.00 |
create: add vision capability detection and fix capability i |
|
— |
2026-03-17 |
| pr |
0.00 |
mlx: add multimodal pipeline infrastructure for vision and a |
|
— |
2026-03-17 |
| pr |
0.00 |
Fix RotatingKVCache trim and wrap handling for sliding windo |
|
— |
2026-03-17 |
| pr |
0.00 |
pull: refine safetensors pull |
|
— |
2026-03-18 |
| pr |
0.00 |
Reduce per-call tokenizer overhead by 3-5× |
|
— |
2026-02-07 |
| pr |
0.00 |
mlxrunner: share KV cache across conversations with common p |
|
— |
2026-03-16 |
| pr |
0.00 |
cmd/launch: skip redundant config writes when model unchange |
|
— |
2026-03-18 |
| pr |
0.00 |
docs: update claude code and openclaw for web search and non |
|
— |
2026-03-18 |
| pr |
0.00 |
launch: fix openclaw not picking up newly selected model |
|
— |
2026-03-18 |
| pr |
0.00 |
launch/docs: update minimax-m2.5 references to m2.7 |
|
— |
2026-03-18 |
| pr |
0.00 |
cmd/tui: add left arrow back navigation in model selector |
|
— |
2026-03-18 |
| pr |
0.00 |
fix: respect format parameter when think is disabled for qwe |
|
— |
2026-03-18 |
| pr |
0.00 |
tui: fix signin on headless Linux systems |
|
— |
2026-03-04 |
| pr |
0.00 |
Fix streaming timeout during tool call composition |
|
— |
2026-03-18 |
| pr |
0.00 |
docs: add multilingual quick-start README |
|
— |
2026-03-18 |
| pr |
0.00 |
x: harden bash approval prompts with parser-based analysis |
|
— |
2026-03-16 |
| pr |
0.00 |
brazilian-portuguese/readme |
|
— |
2026-03-18 |
| pr |
0.00 |
docs: fix incorrect tr command in Linux uninstall instructio |
|
— |
2026-03-18 |
| pr |
0.00 |
docs: fix Linux uninstall command path mangling |
|
— |
2026-03-18 |
| pr |
0.00 |
fix(format): preserve decimal precision for values >= 10 in |
|
— |
2026-03-18 |
| pr |
0.00 |
fix: correctly count CRLF line endings in modelfile parser |
|
— |
2026-03-18 |
| pr |
0.00 |
server: apply format constraint when thinking is disabled |
|
— |
2026-03-06 |
| pr |
0.00 |
launch: disable claude attribution header to preserve KV cac |
|
— |
2026-03-18 |
| pr |
0.00 |
cmd/launch: check for both npm and git before installing Ope |
|
— |
2026-03-16 |
| pr |
0.00 |
fix(docs): correct AMD linux drivers link in linux.mdx |
|
— |
2026-03-17 |
| pr |
0.00 |
WIP |
|
— |
2026-03-18 |
| pr |
0.00 |
Make llama.cpp's cache_prompt parameter configurable |
|
— |
2024-07-18 |
| pr |
0.00 |
runner: enable returning more info from runner processing |
|
— |
2025-02-22 |
| pr |
0.00 |
docs: add steps to implement a new model |
|
— |
2025-02-19 |
| pr |
0.00 |
server: usage api |
|
— |
2026-01-28 |
| pr |
0.00 |
cmd: add /usage to chat to see token consumption |
|
— |
2026-01-28 |
| pr |
0.00 |
Add model eval metrics to /metrics |
|
— |
2025-06-22 |
| pr |
0.00 |
Use LXCFS' formula to compute free memory in a cgroup |
|
— |
2026-01-19 |
| pr |
0.00 |
launch: register websearch for openclaw |
|
— |
2026-03-17 |
| pr |
0.00 |
mlx: add op wrappers for Conv2d, Pad, activations, trig, and |
|
— |
2026-03-17 |
| pr |
0.00 |
model/parsers: treating failed parsing of tool calls as cont |
|
— |
2026-03-17 |
| pr |
0.00 |
cloud_proxy: for the web_search legacy path, flush on newlin |
|
— |
2026-03-17 |
| pr |
0.00 |
mlx: update as of 3/16 |
|
— |
2026-03-12 |
| pr |
0.00 |
README: add iOS chat client |
|
— |
2026-03-17 |
| pr |
0.00 |
mlx: quantized embeddings, fast SwiGLU, and runtime fixes |
|
— |
2026-03-16 |
| pr |
0.00 |
mlx: add prequantized tensor packing + changes for qwen35 |
|
— |
2026-03-16 |
| pr |
0.00 |
readline: harden history persistence |
|
— |
2026-03-17 |
| pr |
0.00 |
fix: treat unparseable qwen tool calls as content instead of |
|
— |
2026-03-17 |
| pr |
0.00 |
server: thread pre-loaded model through scheduleRunner |
|
— |
2026-03-17 |
| pr |
0.00 |
manifest: hoist BlobsPath regex to package level |
|
— |
2026-03-17 |
| pr |
0.00 |
scripts: wait for graphical.target in systemd service |
|
— |
2026-03-17 |
| pr |
0.00 |
runner/ollamarunner: handle sampling errors gracefully |
|
— |
2026-03-17 |
| pr |
0.00 |
fix: correctly count CRLF line endings in modelfile parser |
|
— |
2026-03-17 |
| pr |
0.00 |
Add reranking support |
|
— |
2026-02-09 |
| pr |
0.00 |
fix: prevent negative term width in progress bar |
|
— |
2026-03-16 |
| pr |
0.00 |
docs: add Chinese translation (README.zh.md) |
|
— |
2026-03-16 |
| pr |
0.00 |
ml: rename SSMScan parameter C to CM to resolve cgo naming c |
|
— |
2026-03-07 |
| pr |
0.00 |
tools: fall back to raw JSON parsing when expected tag is mi |
|
— |
2026-02-08 |
| pr |
0.00 |
sched: Model eviction for MLX |
|
— |
2026-03-03 |
| pr |
0.00 |
anthropic: support num_ctx parameter in /v1/messages endpoin |
|
— |
2026-03-17 |
| pr |
0.00 |
fix: Respect %USERPROFILE% for history file path on Windows |
|
— |
2026-03-16 |
| pr |
0.00 |
fix(cmd): correct port typo in TestIsLocalhost |
|
— |
2026-03-17 |
| pr |
0.00 |
launch: fix web search, add web fetch, and enable both for l |
|
— |
2026-03-16 |
| pr |
0.00 |
runner: fix swallowed error in allocModel graph reservation |
|
— |
2026-03-14 |
| pr |
0.00 |
fix: properly propagate error from reserveWorstCaseGraph in |
|
— |
2026-03-15 |
| pr |
0.00 |
fix: propagate error from reserveWorstCaseGraph in allocMode |
|
— |
2026-03-15 |
| pr |
0.00 |
cmd/launch: skip --install-daemon when systemd is unavailabl |
|
— |
2026-03-16 |
| pr |
0.00 |
api: allow localhost connections when auth signing fails |
|
— |
2026-03-16 |
| pr |
0.00 |
cmd: fix port typo in localhost test |
|
— |
2026-03-16 |
| pr |
0.00 |
fix(readline): respect USERPROFILE env var for portable inst |
|
— |
2026-03-14 |
| pr |
0.00 |
fix: respect OLLAMA_MODELS for history file path |
|
— |
2026-03-15 |
| pr |
0.00 |
envconfig: prevent panic when `OLLAMA_ORIGINS` have a tailin |
|
— |
2026-03-13 |
| pr |
0.00 |
fix: handle errors properly in API client and envconfig LogL |
|
— |
2026-03-16 |
| pr |
0.00 |
vulkan: Add memory detection for Intel GPU using Level Zero |
|
— |
2025-10-16 |
| pr |
0.00 |
anthropic: handle thinking disabled case correctly. |
|
— |
2026-03-10 |
| pr |
0.00 |
ggml: update to 0beb8db3a0 |
|
— |
2026-03-15 |
| pr |
0.00 |
re-add OLLAMA_MAX_VRAM |
|
— |
2026-02-21 |
| pr |
0.00 |
integration: allow env overrides for slow runners |
|
— |
2026-03-15 |
| pr |
0.00 |
Revert revert vendor update (Vendor Update to b8353) |
|
— |
2026-02-07 |
| pr |
0.00 |
Enable Intel GPU support with SYCL backend |
|
— |
2025-06-22 |
| pr |
0.00 |
Vulkan flash-attention backport for mask-opt / split-k on WS |
|
— |
2026-03-15 |
| pr |
0.00 |
bench: improve benchmarking tool |
|
— |
2026-02-13 |
| pr |
0.00 |
rocm: update linux to v7.2 |
|
— |
2026-02-24 |
| pr |
0.00 |
Add ROCm 7 support |
|
— |
2025-11-07 |
| pr |
0.00 |
fix(metal): resolve static_assert crash on Apple M5 |
|
— |
2026-03-04 |
| pr |
0.00 |
fix: deadlock when runner needs reload under concurrent load |
|
— |
2026-02-25 |
| pr |
0.00 |
Fix port typo: cmd_test.go |
|
— |
2026-03-15 |
| pr |
0.00 |
cmd/launch: add Octomind integration |
|
— |
2026-03-14 |
| pr |
0.00 |
fix: Correct json.Unmarshal error handling logic |
|
— |
2026-03-14 |
| pr |
0.00 |
fix(readline): respect USERPROFILE env var for portable inst |
|
— |
2026-03-14 |
| pr |
0.00 |
fitcheck: add hardware fit-check and model compatibility ran |
|
— |
2026-03-14 |
| pr |
0.00 |
fix: Validate message role in CreateRequest |
|
— |
2026-03-14 |
