Swarms Contributors Portal

1570

Rank #1

elder-plinius

Contributor

258

Rank #2

dependabot[bot]

Bot

201

Rank #3

IlumCI

Contributor

174

Rank #4

harshalmore31

Contributor

132

Rank #5

evelynmitchell

Contributor

119

Rank #6

Wyatt-Stanke

Contributor

102

Rank #7

Steve-Dusty

Contributor

Rank #8

ayaangazali

Contributor

Rank #9

ascender1729

Contributor

Rank #10

adichaudhary

Contributor

Rank #11

aparekh02

Contributor

Rank #12

hughiwnl

Contributor

Rank #13

sambhavnoobcoder

Contributor

Rank #14

ZackBradshaw

Contributor

Rank #15

GoldenWind8

Contributor

Rank #16

Wxysnx

Contributor

Rank #17

nathan-d

Contributor

Rank #18

vyomakesh09

Contributor

Rank #19

Occupying-Mars

Contributor

Rank #20

PrinceThummar011

Contributor

Rank #21

patrickbdevaney

Contributor

Rank #22

w-zz-w-zz-w

Contributor

Rank #23

filip-michalsky

Contributor

Rank #24

vidithsalla

Contributor

Rank #25

chethanuk

Contributor

Rank #26

simpleqt

Contributor

Rank #27

gilbertoaceville

Contributor

Rank #28

raunitgrey7

Contributor

Rank #29

nicorne

Contributor

Rank #30

eltociear

Contributor

Rank #31

Fadope1

Contributor

Rank #32

adtygan

Contributor

Rank #33

thecaptain789

Contributor

Rank #34

seigot

Contributor

Rank #35

cyberholics

Contributor

Rank #36

nullonesix

Contributor

Rank #37

exvul-nolan

Contributor

Rank #38

nictuku

Contributor

Rank #39

kuant

Contributor

Rank #40

krankos

Contributor

Rank #41

idreesaziz

Contributor

Rank #42

grit-app[bot]

Bot

Rank #43

argentpapa

Contributor

Rank #44

feizhuzheng

Contributor

Rank #45

RinZ27

Contributor

Rank #46

RahulK4102

Contributor

Rank #47

Nishant-k-sagar

Contributor

Rank #48

MycCellium420

Contributor

Rank #49

MalikHaroonKhokhar

Contributor

Rank #50

lidashu

Contributor

Rank #51

cursoragent

Contributor

Rank #52

bookofbash

Contributor

Rank #53

AlexanderLavelle

Contributor

Steve-Dusty•Opened about 7 hours ago

Rank #54

Active Tasks

#2193 [Bug][DebateWithJudge] run() and batched_run() reject img/imgs, while the telemetry decorator declares it captures them

#2168 [Cleanup][Agent] Tool results are recorded twice: drop the 13 'Tool Executor' prose rows now that Conversation holds typed tool rows

#2165 [FEAT][Autonomous loop] Run independent tool calls in parallel, with same-file calls kept in order

#2164 [FEAT][Conversation] Represent tool calls and tool results in Conversation so the parallel Transcript can be deleted

#2163 [FEAT][Autonomous loop] Per-tool permission policy (allow / deny / ask) and a workspace sandbox, replacing the bash blocklist

#2162 [FEAT][Autonomous loop] The file-tool surface a coding agent needs: edit_file, glob, windowed read_file, read-before-write

#2127 [FEAT] Load multiple marketplace skills from a list of .md URLs

prompts

kyegomez•Opened 5 days ago

#2126 [Bug][Dependencies] Every non-streaming completion emits Pydantic serializer warnings from litellm's logging path

kyegomez•Opened 6 days ago

#2122 [Bug][batch_agent_execution][Raises on every call: imgs=None is zipped, and a 3-tuple is unpacked into two names]

Steve-Dusty•Opened 7 days ago

#2070 [BUG][SocialAlgorithms][run_async always raises ValueError: the default timeout path uses signal, which is main-thread only]

Steve-Dusty•Opened 11 days ago

#2055 [BUG][HierarchicalSwarm][The director plan is recorded as a raw tool-call rendering, which every worker then reads as prose]

#2054 [BUG][Multi-Agent Structures][Eleven structures never reset their Conversation per task, and two fan run() across threads sharing one]

#2044 [BUG][MultiAgentRouter][Only the first selected agent response is recorded; the rest are run, paid for, and discarded]

#2041 [BUG][Multi-Agent Structures][Conversation is never reset per task, so batch and concurrent helpers leak history and race on shared state]

#2029 [BUG][Multi-Agent Structures][Every structure flattens the shared conversation into one user block, defeating the Agent-side transcript fix]

#2028 [BUG][CLI] --question-agent-model-name and --worker-model-name help text says "default: gpt-4o-mini" but the actual default is gpt-5.4

kyegomez•Opened 14 days ago

#2006 CouncilAsAJudge results → portable EvalPort ResultSet format

adhabnr-ux•Opened 15 days ago

#2003 [FEAT] Skill accretion: compile successful step sequences into searchable skills

#2002 [FEAT] Tool synthesis: let the agent write and register a tool at runtime

#2001 [FEAT] Adapt iteration budget and sampling to observed task difficulty

#2000 [FEAT] Plan-shape learning: seed planning with skeletons that previously worked

#1999 [FEAT] Use tool-success statistics as a ranking prior in tool_search

#1998 [FEAT] Persist lessons_learned to MEMORY.md instead of discarding it

memory

#1997 [FEAT] Budget-aware degradation: wind down gracefully instead of hitting a wall

#1996 [FEAT] Escalating retry ladder instead of re-running the identical failed call

structs

#1995 [FEAT] Failure-triggered replanning: repair the plan instead of cascading skips

ayaangazali•Opened 16 days ago

#1994 [Bug] Agent.save() and Agent.load() build different paths, so state can never be read back

#1989 [BUG] Tool schemas are duplicated into the conversation as an assistant turn

structs

#1988 [FEAT] Conversation cannot represent tool calls, forcing agent loops to keep a parallel transcript

#1986 [FEAT] Support interrupt and mid-run steering in autonomous mode

#1985 [FEAT] Add a verification field to the plan schema so "done" means checked

#1980 [FEAT] Replace the bash blocklist with a permission model and workspace sandbox

#1979 [FEAT] Add an edit_file tool with exact-string replacement

#1976 [BUG] No cost or call ceiling: worst case is ~2000 full-history LLM calls

#1975 [BUG] Autonomous agent system prompt freezes the timestamp at import time

prompts

#1974 [BUG] Loop reports "All subtasks completed" after abandoning incomplete subtasks

#1972 [BUG] _generate_final_summary returns inconsistent types depending on which branch fires

structs

#1970 [BUG] run_bash and the file tools resolve paths against different roots

#1969 [BUG] run_bash blocklist rejects benign commands and is trivially bypassed

#1967 [BUG] Subtask priority is parsed and displayed but never affects execution order

vidithsalla•Opened 18 days ago

#1951 [Bug][AgentRearrange] concurrent_run shares task state and silently truncates image batches

#1947 [Bug] autoswarm max_loops validation accepts booleans and silently skips falsy values

kyegomez•Opened 18 days ago

#1908 [Bug][HeavySwarm Dashboard] final status does not reflect agent failures

biancam5•Opened 21 days ago

#1906 [Bug][SkillOrchestra] run() silently drops imgs and execution kwargs before agent execution