Skip to content

Make your agents learn from experience. One protocol for weights, harness and routing.

Python · active 2026-03-312026-06-12 (UTC)

Complete coverage26,349 / 26,349 hourly files (100%) · 2 absent upstream2023-08-152026-08-16 (UTC)
Events
111
Pushes
23
Pull requests
7
Issues
37
Stars
4
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 74 days from 2026-03-31 to 2026-06-12. Pushes: 23 total, peak 9 in a day. Pull requests: 7 total, peak 3 in a day. Issues: 37 total, peak 23 in a day. Comments: 20 total, peak 10 in a day. Stars: 4 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
bordeauxred642116
gemini-code-assist[bot]150012
tianyibigdata7121
kiranannadatha85031
dantp-ai3110

Recent activity

Latest issues, pull requests and releases

  • Pull request#65dantp-ai2026-06-10 23:35
  • Pull request#51kiranannadatha82026-04-20 23:46
  • Issue#40dantp-ai2026-04-20 11:11
    Refactor: extract common base for purple-agent adapters (CAR + entropic)
  • Pull request#58kiranannadatha82026-04-20 00:37
  • Issue#56bordeauxred2026-04-19 22:49
    Framework integrations (umbrella): LangChain, LlamaIndex, CrewAI, AutoGen, PydanticAI
  • Issue#56bordeauxred2026-04-19 22:49
    Framework integrations (umbrella): LangChain, LlamaIndex, CrewAI, AutoGen, PydanticAI
  • Issue#56bordeauxred2026-04-19 22:49
    Framework integrations (umbrella): LangChain, LlamaIndex, CrewAI, AutoGen, PydanticAI
  • Issue comment#51bordeauxred2026-04-19 22:08
    refactor: extract common base for purple-agent adapters (#40)
  • Issue#54bordeauxred2026-04-19 21:57
    Research direction: Hyperagent for learner tuning
  • Issue#54bordeauxred2026-04-19 21:57
    Research direction: Hyperagent for learner tuning
  • Issue#53bordeauxred2026-04-19 21:56
    Benchmark adapters (umbrella): SWE-bench, WebArena, GAIA, AgentBench, BrowseComp
  • Issue#52bordeauxred2026-04-19 21:56
    Observability integrations (umbrella): W&B, MLflow, Langfuse, OpenTelemetry, Phoenix
  • Issue#52bordeauxred2026-04-19 21:56
    Observability integrations (umbrella): W&B, MLflow, Langfuse, OpenTelemetry, Phoenix
  • Issue#52bordeauxred2026-04-19 21:56
    Observability integrations (umbrella): W&B, MLflow, Langfuse, OpenTelemetry, Phoenix
  • Issue#28bordeauxred2026-04-19 21:25
    Add ruff + pre-commit (format + E,F,I)
  • Pull request#27kiranannadatha82026-04-19 21:25
  • Issue#32tianyibigdata2026-04-19 20:23
    Update README, version, changelog, dependency bounds, and limitations for launch
  • Pull request#47tianyibigdata2026-04-19 20:04
  • Pull request#45tianyibigdata2026-04-19 19:55
  • Issue#31bordeauxred2026-04-19 16:16
    Ship installed no-key math demo and verify it from the wheel
  • Issue comment#43bordeauxred2026-04-19 15:22
    Ship installed no-key math demo and verify it from the wheel
  • Issue#42bordeauxred2026-04-19 13:29
    Docs: privacy & redaction of traces and tool calls
  • Issue#41bordeauxred2026-04-19 00:22
    Roadmap (umbrella): mode='full', router productionization, weights hardening, ProblemEnv abstraction
  • Issue#40bordeauxred2026-04-19 00:22
    Refactor: extract common base for purple-agent adapters (CAR + entropic)
  • Issue#38bordeauxred2026-04-19 00:22
    Refactor: split monolithic learning_layers/harness.py and resolve core->layers import inversion

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 4 stars here means stars gained during the window, not the repo's star count.