Owner

kyegomez

43 indexed repositories · View on GitHub

OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Python · 14901 stars
swarms
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

Python · 7183 stars
tree-of-thoughts
Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning ...

Python · 4588 stars
awesome-multi-agent-papers
A compilation of the best multi-agent papers

TeX · 1680 stars
LongNet
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

Python · 727 stars
RT-2
Democratization of RT-2 "RT-2: New model translates vision and language into action"

Python · 584 stars
Med-PaLM
Towards Generalist Biomedical AI

Python · 434 stars
Sophia
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

Python · 383 stars
CM3Leon
An open source implementation of "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", an all-new multi modal ...

Python · 366 stars
PALM-E
Implementation of "PaLM-E: An Embodied Multimodal Language Model"

Python · 338 stars
AttentionIsOFFByOne
Implementation of "Attention Is Off By One" by Evan Miller

Python · 198 stars
Andromeda
An all-new Language Model That Processes Ultra-Long Sequences of 100,000+ Ultra-Fast

Python · 151 stars
the-compiler
Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

Python · 144 stars
FlashAttention20
Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels

Python · 115 stars
Algorithm-Of-Thoughts
My implementation of "Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models"

Python · 100 stars
PALI
Democratization of "PaLI: A Jointly-Scaled Multilingual Language-Image Model"

Python · 94 stars
RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation" An next generation robot LLM

Python · 92 stars
phi-1
Plug in and play implementation of " Textbooks Are All You Need", ready for training, inference, and dataset generation

Python · 74 stars
Kosmos-X
The Next Generation Multi-Modality Superintelligence

Python · 71 stars
StarlightVision
A multi-modal AI Model that can generate high quality novel videos with text, images, or video clips.

Python · 64 stars
23 more repositories live on View on GitHub

Beginner friendly Everything

Open All

[BUG][AutonomousAgentLoop][tool_search returns irrelevant tools and the subtask stalls instead of continuing] Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

kyegomez/swarms#2298 · Opened Sep 17, 2026
[BUG] AUTO_GEN_PROMPT Marks Swarm Description as Optional, but YAML Loader Requires It Open

bug

kyegomez/swarms#2283 · 2 comments · 1 assignee · Opened Sep 15, 2026
Verify evals on Papers with Code Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

kyegomez/RT-2#31 · Opened Sep 14, 2026
[BUGF][one_on_one_debate][Retain the first answer in default output] Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

kyegomez/swarms#2243 · 3 comments · Opened Sep 12, 2026
[FEAT] Add an opt-in Codex CLI backend configurable through Agent/YAML Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

kyegomez/swarms#2222 · 1 comment · Opened Sep 10, 2026
[BUG][PlannerGeneratorEvaluator] The entire shared state file is pasted into every agent call, O(steps² × retries) (#2053 follow-up) Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 52/100

kyegomez/swarms#2202 · Opened Sep 8, 2026
[BUG][LLMCouncil] The Chairman gets the whole council as one user blob (#2053 follow-up) Open

bug

Difficulty 2/5 Half a day Newbie friendliness 82/100

kyegomez/swarms#2200 · 1 comment · Opened Sep 8, 2026
[Bug][Memory] persistent_memory injects the whole MEMORY.md on every start, so startup context grows by ~5k characters per session, forever Open

Difficulty 3/5 1-2 days Newbie friendliness 76/100

kyegomez/swarms#2198 · Opened Sep 8, 2026
[First-time contributor] Looking for beginner-friendly issues to contribute Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

kyegomez/swarms#2194 · 1 comment · Opened Sep 8, 2026
[Bug][DebateWithJudge] run() and batched_run() reject img/imgs, while the telemetry decorator declares it captures them Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

kyegomez/swarms#2193 · 1 comment · Opened Sep 7, 2026
[Cleanup][Agent] Tool results are recorded twice: drop the 13 'Tool Executor' prose rows now that Conversation holds typed tool rows Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 74/100

kyegomez/swarms#2168 · Opened Sep 5, 2026
[FEAT][Autonomous loop] Run independent tool calls in parallel, with same-file calls kept in order Open

FEAT

Difficulty 5/5 Over a week Newbie friendliness 45/100

kyegomez/swarms#2165 · Opened Sep 5, 2026
[FEAT][Conversation] Represent tool calls and tool results in Conversation so the parallel Transcript can be deleted Open

FEAT

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#2164 · Opened Sep 5, 2026
[FEAT][Autonomous loop] Per-tool permission policy (allow / deny / ask) and a workspace sandbox, replacing the bash blocklist Open

FEAT

Difficulty 5/5 Over a week Newbie friendliness 38/100

kyegomez/swarms#2163 · Opened Sep 5, 2026
[FEAT][Autonomous loop] The file-tool surface a coding agent needs: edit_file, glob, windowed read_file, read-before-write Open

FEAT

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#2162 · Opened Sep 5, 2026
[FEAT] Load multiple marketplace skills from a list of .md URLs Open

agents FEAT prompts

Difficulty 4/5 3-5 days Newbie friendliness 45/100

kyegomez/swarms#2127 · Opened Sep 2, 2026
[Bug][Dependencies] Every non-streaming completion emits Pydantic serializer warnings from litellm's logging path Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

kyegomez/swarms#2126 · 1 comment · Opened Sep 1, 2026
[BUG][SocialAlgorithms][run_async always raises ValueError: the default timeout path uses signal, which is main-thread only] Open

Difficulty 4/5 3-5 days Newbie friendliness 72/100

kyegomez/swarms#2070 · Opened Aug 27, 2026
[BUG][HierarchicalSwarm][The director plan is recorded as a raw tool-call rendering, which every worker then reads as prose] Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 74/100

kyegomez/swarms#2055 · Opened Aug 25, 2026
[BUG][Multi-Agent Structures][Eleven structures never reset their Conversation per task, and two fan run() across threads sharing one] Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 48/100

kyegomez/swarms#2054 · Opened Aug 25, 2026
[BUG][MultiAgentRouter][Only the first selected agent response is recorded; the rest are run, paid for, and discarded] Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 72/100

kyegomez/swarms#2044 · Opened Aug 25, 2026
[BUG][Multi-Agent Structures][Conversation is never reset per task, so batch and concurrent helpers leak history and race on shared state] Open

bug

Difficulty 5/5 Over a week Newbie friendliness 45/100

kyegomez/swarms#2041 · 1 comment · Opened Aug 25, 2026
[BUG][Multi-Agent Structures][Every structure flattens the shared conversation into one user block, defeating the Agent-side transcript fix] Open

bug

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#2029 · 1 comment · Opened Aug 25, 2026
CouncilAsAJudge results → portable EvalPort ResultSet format Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

kyegomez/swarms#2006 · 1 comment · Opened Aug 23, 2026
[FEAT] Skill accretion: compile successful step sequences into searchable skills Open

agents enhancement tools

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#2003 · Opened Aug 23, 2026
[FEAT] Tool synthesis: let the agent write and register a tool at runtime Open

enhancement tools

Difficulty 5/5 Over a week Newbie friendliness 25/100

kyegomez/swarms#2002 · Opened Aug 23, 2026
[FEAT] Adapt iteration budget and sampling to observed task difficulty Open

agents enhancement

Difficulty 5/5 Over a week Newbie friendliness 45/100

kyegomez/swarms#2001 · Opened Aug 23, 2026
[FEAT] Plan-shape learning: seed planning with skeletons that previously worked Open

agents enhancement

Difficulty 5/5 Over a week Newbie friendliness 30/100

kyegomez/swarms#2000 · Opened Aug 23, 2026
[FEAT] Use tool-success statistics as a ranking prior in tool_search Open

enhancement tools

Difficulty 5/5 Over a week Newbie friendliness 42/100

kyegomez/swarms#1999 · Opened Aug 23, 2026
[FEAT] Persist lessons_learned to MEMORY.md instead of discarding it Open

agents enhancement memory

Difficulty 4/5 3-5 days Newbie friendliness 55/100

kyegomez/swarms#1998 · Opened Aug 23, 2026
[FEAT] Budget-aware degradation: wind down gracefully instead of hitting a wall Open

agents enhancement priority:high

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#1997 · Opened Aug 23, 2026
[FEAT] Escalating retry ladder instead of re-running the identical failed call Open

enhancement priority:high structs

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#1996 · Opened Aug 23, 2026
[FEAT] Failure-triggered replanning: repair the plan instead of cascading skips Open

agents enhancement priority:high

Difficulty 3/5 1-2 days Newbie friendliness 68/100

kyegomez/swarms#1995 · Opened Aug 23, 2026
[Bug] Agent.save() and Agent.load() build different paths, so state can never be read back Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

kyegomez/swarms#1994 · Opened Aug 23, 2026
[BUG] Tool schemas are duplicated into the conversation as an assistant turn Open

bug structs tools

Difficulty 1/5 Under an hour Newbie friendliness 88/100

kyegomez/swarms#1989 · 1 comment · Opened Aug 23, 2026
[FEAT] Conversation cannot represent tool calls, forcing agent loops to keep a parallel transcript Open

enhancement priority:high structs tech-debt

Difficulty 4/5 3-5 days Newbie friendliness 52/100

kyegomez/swarms#1988 · Opened Aug 23, 2026
[FEAT] Support interrupt and mid-run steering in autonomous mode Open

agents enhancement

Difficulty 5/5 Over a week Newbie friendliness 45/100

kyegomez/swarms#1986 · Opened Aug 22, 2026
[FEAT] Add a verification field to the plan schema so "done" means checked Open

agents enhancement priority:high tools

Difficulty 4/5 3-5 days Newbie friendliness 48/100

kyegomez/swarms#1985 · Opened Aug 22, 2026
[FEAT] Execute independent tool calls in parallel Open

agents enhancement priority:high

Difficulty 4/5 3-5 days Newbie friendliness 72/100

kyegomez/swarms#1984 · Opened Aug 22, 2026
[FEAT] Enforce a read-before-write invariant on file edits Open

enhancement priority:high structs tools

Difficulty 4/5 3-5 days Newbie friendliness 55/100

kyegomez/swarms#1982 · 1 comment · Opened Aug 22, 2026
[FEAT] Add offset/limit and line numbers to read_file Open

enhancement priority:high structs tools

Difficulty 3/5 1-2 days Newbie friendliness 68/100

kyegomez/swarms#1981 · Opened Aug 22, 2026
[FEAT] Replace the bash blocklist with a permission model and workspace sandbox Open

enhancement priority:high structs tools

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#1980 · 1 comment · Opened Aug 22, 2026
[FEAT] Add an edit_file tool with exact-string replacement Open

enhancement priority:high structs tools

Difficulty 3/5 1-2 days Newbie friendliness 76/100

kyegomez/swarms#1979 · Opened Aug 22, 2026
[BUG] No cost or call ceiling: worst case is ~2000 full-history LLM calls Open

agents bug priority:high

Difficulty 4/5 3-5 days Newbie friendliness 48/100

kyegomez/swarms#1976 · Opened Aug 22, 2026
[BUG] Loop reports "All subtasks completed" after abandoning incomplete subtasks Open

agents bug priority:high

Difficulty 4/5 3-5 days Newbie friendliness 68/100

kyegomez/swarms#1974 · Opened Aug 22, 2026
[BUG] run_bash and the file tools resolve paths against different roots Open

bug priority:high structs tools

Difficulty 4/5 3-5 days Newbie friendliness 65/100

kyegomez/swarms#1970 · Opened Aug 22, 2026
[BUG] run_bash blocklist rejects benign commands and is trivially bypassed Open

bug priority:high structs tools

Difficulty 5/5 Over a week Newbie friendliness 35/100

kyegomez/swarms#1969 · Opened Aug 22, 2026
[BUG] Subtask priority is parsed and displayed but never affects execution order Open

agents bug

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

kyegomez/swarms#1967 · Opened Aug 22, 2026
[Bug][AgentRearrange] concurrent_run shares task state and silently truncates image batches Open

Difficulty 3/5 1-2 days Newbie friendliness 78/100

kyegomez/swarms#1951 · 2 comments · Opened Aug 21, 2026
[Bug] autoswarm max_loops validation accepts booleans and silently skips falsy values Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

kyegomez/swarms#1947 · 1 comment · Opened Aug 20, 2026

Showing the newest 100

This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.

Open advanced filter

kyegomez

Showing the newest 100

Get new issues in your inbox